¶
DESCRIPTION AND ROADMAP OF THE PROJECT
In this project, I will compare the performance of two machine learning algorithms: k-Nearest Neighbours (k-NN) and Random Forest. The dataset has 1400 samples with 25 features each. The first column is the sample ID, the second column is the label (with five possible values) and the rest are the characteristics. In order to obtain a better result and to understand the available data better, an exploratory data analysis and the application of unsupervised learning methods are carried out. Finally, the implementation of a neural network is useful to make a comparison with a more complex model.
- LIBRARIES
- OPENING THE DATASET
EXPLORATORY DATA ANALYSIS
2.1 DATA TYPE AND MISSING VALUES CHECK
2.2 COMPUTATION AND VISUALIZATION OF MEAN, STD, QUANTILES, MAX, MIN, CORRELATION MATRIX
2.3 ADDITIONAL CHECK TO SEE IF DATA IS NORMALIZED
CHECK IF CLASSES ARE BALANCED
- UNSUPERVISED LEARNING METHODS
CLASSIFIERS
4.1 RANDOM FOREST
4.1.1 SIMPLE RANDOM FOREST
4.1.2 RANDOM FOREST WITH GRID SEARCH
4.1.3 RANDOM FOREST WITH RANDOM SEARCH
4.1.4 RANDOM FOREST WITH BAYESIAN SEARCH
4.1.5 RANDOM FOREST MODEL SELECTION
4.2 KNN
4.2.1 SIMPLE KNN
4.2.2 KNN WITH GRID SEARCH
4.2.3 KNN WITH RANDOM SEARCH
4.2.4 KNN WITH BAYESIAN SEARCH
4.2.5 KNN MODEL SELECTION
4.3 FINAL MODEL SELECTION
4.4 NEURAL NETWORK (EXTRA TOPIC)
- PREDICTIONS
- CONCLUSIONS
¶
- LIBRARIES
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import scipy
import sklearn
from scipy.stats import kurtosis, skew
from sklearn import metrics
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans , AgglomerativeClustering, DBSCAN
from sklearn.ensemble import RandomForestClassifier, VotingClassifier
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
from sklearn.model_selection import cross_val_score,StratifiedKFold, train_test_split,LeaveOneOut, GridSearchCV, KFold, RandomizedSearchCV
from sklearn.svm import SVC, NuSVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.preprocessing import StandardScaler, MinMaxScaler
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score, f1_score, recall_score, precision_score
from skopt import BayesSearchCV
from skopt.space import Real, Integer, Categorical
import itertools
import os
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
import torch.optim as optim
¶
- OPENING THE DATASET
I start opening the dataset with the read_csv method in order to get a dataframe. I use as the index the sample id column.
df = pd.read_csv('mldata_0003195463/mldata_0003195463.csv', index_col=0)
df
| label | feature_1 | feature_2 | feature_3 | feature_4 | feature_5 | feature_6 | feature_7 | feature_8 | feature_9 | ... | feature_16 | feature_17 | feature_18 | feature_19 | feature_20 | feature_21 | feature_22 | feature_23 | feature_24 | feature_25 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | 0.880273 | 0.442573 | -2.032819 | -0.576659 | -4.358051 | 2.376050 | 0.878844 | 0.880273 | -1.874594 | ... | 5.111025 | -3.170193 | -1.846344 | 6.816500 | -0.325096 | 0.356847 | 0.267963 | 0.128522 | 4.710026 | 2.439719 |
| 1 | 1 | 1.313825 | -1.949632 | 1.070599 | 1.394479 | -0.059726 | -2.975673 | 3.306127 | 1.313825 | 4.609667 | ... | -4.540766 | -4.718089 | -0.490495 | 3.271247 | 0.120484 | 0.388111 | 0.166516 | 1.187520 | -4.999382 | 2.578916 |
| 2 | 0 | -1.009061 | -0.301009 | 5.641678 | -0.921311 | -2.646763 | -1.947697 | -0.578194 | -1.009061 | 1.917913 | ... | 0.663454 | 0.724729 | 0.229717 | 2.032490 | 0.905951 | 0.175052 | -2.693749 | -3.747243 | 5.988060 | 2.321502 |
| 3 | 0 | -0.239631 | 3.031876 | -1.614844 | -1.091440 | -0.776343 | 0.390649 | -0.113804 | -0.239631 | -2.506136 | ... | 5.037567 | 0.179098 | -1.320429 | 3.930034 | 0.073331 | -1.778206 | -0.786323 | -2.204570 | 5.601020 | -0.230172 |
| 4 | 3 | 2.612405 | 0.535401 | -0.396174 | 0.251268 | 4.729981 | 1.030001 | -2.412348 | 2.612405 | 3.542474 | ... | -2.521146 | -0.048739 | -0.010981 | -6.330675 | 1.710562 | -0.306278 | 0.112979 | 2.182430 | -4.726831 | -1.039056 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1395 | 4 | 1.658674 | -2.182582 | 1.361128 | -0.223131 | 1.381046 | 1.378637 | 1.010512 | 1.658674 | 0.911761 | ... | -3.797807 | 1.035576 | 3.116603 | -3.478307 | -2.576972 | 1.423271 | -0.985356 | -1.662373 | 0.367540 | 1.185928 |
| 1396 | 3 | 1.343677 | -0.084420 | -0.678494 | 1.063410 | 2.486721 | 2.675759 | 0.063485 | 1.343677 | 6.019151 | ... | 2.674485 | 2.995162 | -0.128158 | -3.063000 | -3.342745 | -1.010822 | -1.358623 | 1.126761 | -5.258127 | -0.244412 |
| 1397 | 0 | -1.199296 | 4.393630 | 0.087376 | -0.706097 | 2.294865 | -0.709506 | -1.220693 | -1.199296 | 0.552521 | ... | -0.104632 | 3.663284 | 0.118288 | 6.718347 | 3.372529 | -0.066236 | -0.165354 | -0.497060 | 8.260052 | 5.352153 |
| 1398 | 3 | 0.444458 | -5.569485 | -2.959195 | -0.197783 | -1.033010 | -0.518803 | 3.340311 | 0.444458 | 0.795092 | ... | 3.725220 | -2.332213 | 0.650232 | 5.851846 | 6.574953 | 1.820581 | -0.218203 | 0.403429 | -3.459758 | 0.700423 |
| 1399 | 4 | -0.160659 | 1.186228 | -1.238557 | -1.203545 | 0.084697 | -0.178147 | 0.750582 | -0.160659 | -0.904650 | ... | 4.180642 | 0.364106 | 1.047320 | 0.269967 | -0.071741 | 0.273339 | -1.399230 | -2.708364 | 0.516151 | -1.190896 |
1400 rows × 26 columns
I separate the dataset into two datasets: one containing all the features and data points, while the second containing the labels for each data point. The separation will be incredibly useful during the training of the model.
df_data_points = df.iloc[:, 1:]
df_data_points
| feature_1 | feature_2 | feature_3 | feature_4 | feature_5 | feature_6 | feature_7 | feature_8 | feature_9 | feature_10 | ... | feature_16 | feature_17 | feature_18 | feature_19 | feature_20 | feature_21 | feature_22 | feature_23 | feature_24 | feature_25 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.880273 | 0.442573 | -2.032819 | -0.576659 | -4.358051 | 2.376050 | 0.878844 | 0.880273 | -1.874594 | 0.244483 | ... | 5.111025 | -3.170193 | -1.846344 | 6.816500 | -0.325096 | 0.356847 | 0.267963 | 0.128522 | 4.710026 | 2.439719 |
| 1 | 1.313825 | -1.949632 | 1.070599 | 1.394479 | -0.059726 | -2.975673 | 3.306127 | 1.313825 | 4.609667 | 0.376011 | ... | -4.540766 | -4.718089 | -0.490495 | 3.271247 | 0.120484 | 0.388111 | 0.166516 | 1.187520 | -4.999382 | 2.578916 |
| 2 | -1.009061 | -0.301009 | 5.641678 | -0.921311 | -2.646763 | -1.947697 | -0.578194 | -1.009061 | 1.917913 | -0.108523 | ... | 0.663454 | 0.724729 | 0.229717 | 2.032490 | 0.905951 | 0.175052 | -2.693749 | -3.747243 | 5.988060 | 2.321502 |
| 3 | -0.239631 | 3.031876 | -1.614844 | -1.091440 | -0.776343 | 0.390649 | -0.113804 | -0.239631 | -2.506136 | 0.492805 | ... | 5.037567 | 0.179098 | -1.320429 | 3.930034 | 0.073331 | -1.778206 | -0.786323 | -2.204570 | 5.601020 | -0.230172 |
| 4 | 2.612405 | 0.535401 | -0.396174 | 0.251268 | 4.729981 | 1.030001 | -2.412348 | 2.612405 | 3.542474 | 1.402761 | ... | -2.521146 | -0.048739 | -0.010981 | -6.330675 | 1.710562 | -0.306278 | 0.112979 | 2.182430 | -4.726831 | -1.039056 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1395 | 1.658674 | -2.182582 | 1.361128 | -0.223131 | 1.381046 | 1.378637 | 1.010512 | 1.658674 | 0.911761 | 0.310275 | ... | -3.797807 | 1.035576 | 3.116603 | -3.478307 | -2.576972 | 1.423271 | -0.985356 | -1.662373 | 0.367540 | 1.185928 |
| 1396 | 1.343677 | -0.084420 | -0.678494 | 1.063410 | 2.486721 | 2.675759 | 0.063485 | 1.343677 | 6.019151 | 1.785352 | ... | 2.674485 | 2.995162 | -0.128158 | -3.063000 | -3.342745 | -1.010822 | -1.358623 | 1.126761 | -5.258127 | -0.244412 |
| 1397 | -1.199296 | 4.393630 | 0.087376 | -0.706097 | 2.294865 | -0.709506 | -1.220693 | -1.199296 | 0.552521 | 0.732084 | ... | -0.104632 | 3.663284 | 0.118288 | 6.718347 | 3.372529 | -0.066236 | -0.165354 | -0.497060 | 8.260052 | 5.352153 |
| 1398 | 0.444458 | -5.569485 | -2.959195 | -0.197783 | -1.033010 | -0.518803 | 3.340311 | 0.444458 | 0.795092 | 0.008757 | ... | 3.725220 | -2.332213 | 0.650232 | 5.851846 | 6.574953 | 1.820581 | -0.218203 | 0.403429 | -3.459758 | 0.700423 |
| 1399 | -0.160659 | 1.186228 | -1.238557 | -1.203545 | 0.084697 | -0.178147 | 0.750582 | -0.160659 | -0.904650 | 0.409299 | ... | 4.180642 | 0.364106 | 1.047320 | 0.269967 | -0.071741 | 0.273339 | -1.399230 | -2.708364 | 0.516151 | -1.190896 |
1400 rows × 25 columns
df_data_points.shape # as pointed out in the instructions the dataset (excluded labels) is made of 25 features and 1400 data points
(1400, 25)
df_labels = df.iloc[:, 0]
df_labels
0 0
1 1
2 0
3 0
4 3
..
1395 4
1396 3
1397 0
1398 3
1399 4
Name: label, Length: 1400, dtype: int64
The transpose dataset of samples and of labels are instead the following
df_data_points_tr = df_data_points.T
df_data_points_tr
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | ... | 1390 | 1391 | 1392 | 1393 | 1394 | 1395 | 1396 | 1397 | 1398 | 1399 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| feature_1 | 0.880273 | 1.313825 | -1.009061 | -0.239631 | 2.612405 | 0.037314 | 2.010636 | 1.986206 | 0.006886 | -4.488281 | ... | -0.820145 | -1.729645 | -1.317473 | 0.091772 | 0.937398 | 1.658674 | 1.343677 | -1.199296 | 0.444458 | -0.160659 |
| feature_2 | 0.442573 | -1.949632 | -0.301009 | 3.031876 | 0.535401 | -0.206636 | 0.621676 | 4.117393 | -0.548541 | 0.012253 | ... | -0.837771 | -0.531008 | -2.375530 | -0.624140 | 3.415699 | -2.182582 | -0.084420 | 4.393630 | -5.569485 | 1.186228 |
| feature_3 | -2.032819 | 1.070599 | 5.641678 | -1.614844 | -0.396174 | 3.805659 | -5.766030 | -2.116423 | -1.114819 | 0.168275 | ... | 3.147020 | 3.084188 | 0.452407 | 1.703822 | 0.193878 | 1.361128 | -0.678494 | 0.087376 | -2.959195 | -1.238557 |
| feature_4 | -0.576659 | 1.394479 | -0.921311 | -1.091440 | 0.251268 | -1.248468 | -0.060257 | -1.030494 | -1.044195 | 0.713612 | ... | 1.044003 | -0.132301 | 0.586763 | 1.752429 | 0.932712 | -0.223131 | 1.063410 | -0.706097 | -0.197783 | -1.203545 |
| feature_5 | -4.358051 | -0.059726 | -2.646763 | -0.776343 | 4.729981 | -2.630187 | -2.617304 | 1.891215 | 0.281889 | 0.010156 | ... | -1.181065 | 1.801259 | 0.754335 | -1.361584 | -1.184189 | 1.381046 | 2.486721 | 2.294865 | -1.033010 | 0.084697 |
| feature_6 | 2.376050 | -2.975673 | -1.947697 | 0.390649 | 1.030001 | -3.808977 | -2.106621 | 1.333070 | -0.888954 | 1.291766 | ... | -0.374998 | -0.245327 | -1.686892 | -0.029591 | 2.938863 | 1.378637 | 2.675759 | -0.709506 | -0.518803 | -0.178147 |
| feature_7 | 0.878844 | 3.306127 | -0.578194 | -0.113804 | -2.412348 | -1.709104 | -1.109602 | 0.912973 | 2.562891 | -3.332946 | ... | -0.040821 | -1.421910 | 1.144027 | -0.310815 | -2.194036 | 1.010512 | 0.063485 | -1.220693 | 3.340311 | 0.750582 |
| feature_8 | 0.880273 | 1.313825 | -1.009061 | -0.239631 | 2.612405 | 0.037314 | 2.010636 | 1.986206 | 0.006886 | -4.488281 | ... | -0.820145 | -1.729645 | -1.317473 | 0.091772 | 0.937398 | 1.658674 | 1.343677 | -1.199296 | 0.444458 | -0.160659 |
| feature_9 | -1.874594 | 4.609667 | 1.917913 | -2.506136 | 3.542474 | -1.901907 | 4.176352 | -0.352365 | 3.993937 | 1.284281 | ... | 0.234835 | 3.096202 | 1.827541 | -1.202440 | -1.212045 | 0.911761 | 6.019151 | 0.552521 | 0.795092 | -0.904650 |
| feature_10 | 0.244483 | 0.376011 | -0.108523 | 0.492805 | 1.402761 | 0.205311 | -1.246551 | -0.286358 | -0.215466 | 0.141398 | ... | 0.040927 | -3.070705 | 0.748908 | 1.509786 | -1.360279 | 0.310275 | 1.785352 | 0.732084 | 0.008757 | 0.409299 |
| feature_11 | -0.568563 | -0.642429 | 0.631918 | 0.123358 | 2.102372 | 1.804765 | 1.085559 | -3.084630 | -2.913143 | -1.486520 | ... | -0.726145 | -0.587255 | -1.274088 | -1.070924 | 0.271354 | 1.427420 | 2.612296 | 3.378662 | 4.065548 | -2.006805 |
| feature_12 | -3.958259 | 0.527434 | -0.905757 | -2.559503 | 1.169881 | -0.072967 | 2.088462 | 0.505836 | -0.547933 | 0.655720 | ... | 1.250022 | 1.936665 | -0.652181 | -1.301670 | -2.924451 | 2.547526 | -2.583972 | 1.055483 | 1.847198 | -1.156191 |
| feature_13 | 0.846233 | 2.406618 | 1.901215 | 0.814844 | -1.005312 | 0.698838 | -0.779006 | 1.718272 | -0.721186 | -0.566567 | ... | -0.519731 | 0.077736 | 0.463265 | -0.280210 | -0.898018 | -0.200645 | 2.611102 | -0.742559 | 1.279831 | -0.801016 |
| feature_14 | 7.906497 | 1.275940 | -3.975294 | 2.398946 | -0.229136 | -6.634834 | -2.048398 | 2.433992 | 1.326202 | -1.058776 | ... | -6.728930 | -1.992863 | 4.801895 | 2.404796 | 1.975635 | 5.183851 | 5.040128 | -6.805083 | -1.076242 | 2.433056 |
| feature_15 | 0.835684 | 1.206942 | 0.301467 | 0.399737 | 0.584454 | 0.864146 | 1.552834 | 0.685178 | 0.373199 | 0.245434 | ... | 0.176876 | -0.351053 | 1.137664 | -0.453112 | 1.490879 | -0.608051 | 0.951184 | -0.138551 | -0.193516 | 1.036109 |
| feature_16 | 5.111025 | -4.540766 | 0.663454 | 5.037567 | -2.521146 | -3.521657 | 0.749332 | -0.438854 | 2.135337 | 4.407460 | ... | -0.142716 | -1.753790 | 1.048744 | 2.699760 | 5.922917 | -3.797807 | 2.674485 | -0.104632 | 3.725220 | 4.180642 |
| feature_17 | -3.170193 | -4.718089 | 0.724729 | 0.179098 | -0.048739 | 0.117485 | -0.813414 | 0.704341 | -2.462587 | 1.933163 | ... | 5.272173 | 0.910549 | -1.522661 | 0.720169 | 2.059841 | 1.035576 | 2.995162 | 3.663284 | -2.332213 | 0.364106 |
| feature_18 | -1.846344 | -0.490495 | 0.229717 | -1.320429 | -0.010981 | -1.109924 | -1.336012 | 0.464369 | 0.758567 | -0.225195 | ... | -0.855814 | 1.083912 | 0.278338 | -0.190353 | 0.782890 | 3.116603 | -0.128158 | 0.118288 | 0.650232 | 1.047320 |
| feature_19 | 6.816500 | 3.271247 | 2.032490 | 3.930034 | -6.330675 | 4.948475 | 2.291858 | -1.472067 | 0.506498 | -5.468823 | ... | -1.680982 | -2.708883 | 0.817680 | -0.767239 | 3.523459 | -3.478307 | -3.063000 | 6.718347 | 5.851846 | 0.269967 |
| feature_20 | -0.325096 | 0.120484 | 0.905951 | 0.073331 | 1.710562 | 2.633378 | -4.093771 | -1.642073 | 0.468107 | -2.921080 | ... | 0.477611 | 0.881359 | -0.255975 | 0.046852 | 2.957629 | -2.576972 | -3.342745 | 3.372529 | 6.574953 | -0.071741 |
| feature_21 | 0.356847 | 0.388111 | 0.175052 | -1.778206 | -0.306278 | 1.346645 | 0.430862 | 0.550580 | -0.063203 | -0.045571 | ... | 0.076906 | -1.118559 | -0.590103 | -0.474936 | -1.266574 | 1.423271 | -1.010822 | -0.066236 | 1.820581 | 0.273339 |
| feature_22 | 0.267963 | 0.166516 | -2.693749 | -0.786323 | 0.112979 | -0.104546 | -1.004232 | -0.073920 | -0.658809 | 1.797368 | ... | 0.361732 | 1.181771 | -1.922470 | -0.146421 | 0.140574 | -0.985356 | -1.358623 | -0.165354 | -0.218203 | -1.399230 |
| feature_23 | 0.128522 | 1.187520 | -3.747243 | -2.204570 | 2.182430 | -0.415033 | -1.703285 | 0.336433 | 0.068914 | -3.230154 | ... | -0.143410 | -1.786970 | -2.884640 | -3.145130 | -1.840632 | -1.662373 | 1.126761 | -0.497060 | 0.403429 | -2.708364 |
| feature_24 | 4.710026 | -4.999382 | 5.988060 | 5.601020 | -4.726831 | 9.718475 | 0.445922 | -1.713812 | -7.775547 | -0.546823 | ... | 0.489176 | 0.156532 | -0.578978 | 3.531062 | 8.763727 | 0.367540 | -5.258127 | 8.260052 | -3.459758 | 0.516151 |
| feature_25 | 2.439719 | 2.578916 | 2.321502 | -0.230172 | -1.039056 | 1.988640 | -3.537702 | -0.325273 | 0.068403 | -1.991403 | ... | -0.214643 | 3.283793 | 1.946495 | -0.301800 | 3.841910 | 1.185928 | -0.244412 | 5.352153 | 0.700423 | -1.190896 |
25 rows × 1400 columns
labels_t = df_labels.T
labels_t
0 0
1 1
2 0
3 0
4 3
..
1395 4
1396 3
1397 0
1398 3
1399 4
Name: label, Length: 1400, dtype: int64
¶
- EXPLORATORY DATA ANALYSIS
I now start to perform the exploratory data analysis on my dataset in order to better understand the data itself, see if there are special patterns and look for the distribution
¶
2.1 DATA TYPE AND MISSING VALUES CHECK
I start check if I have all valid values in the dataset and if all of them are integers/floats (as should be according to the instructions)
print("Data Types:\n", df_data_points.dtypes)
Data Types: feature_1 float64 feature_2 float64 feature_3 float64 feature_4 float64 feature_5 float64 feature_6 float64 feature_7 float64 feature_8 float64 feature_9 float64 feature_10 float64 feature_11 float64 feature_12 float64 feature_13 float64 feature_14 float64 feature_15 float64 feature_16 float64 feature_17 float64 feature_18 float64 feature_19 float64 feature_20 float64 feature_21 float64 feature_22 float64 feature_23 float64 feature_24 float64 feature_25 float64 dtype: object
print("Features with Nan values:\n", df_data_points.isna().any())
Features with Nan values: feature_1 False feature_2 False feature_3 False feature_4 False feature_5 False feature_6 False feature_7 False feature_8 False feature_9 False feature_10 False feature_11 False feature_12 False feature_13 False feature_14 False feature_15 False feature_16 False feature_17 False feature_18 False feature_19 False feature_20 False feature_21 False feature_22 False feature_23 False feature_24 False feature_25 False dtype: bool
As it is possible to notice from the previous checks, I have all valid values in my dataset and more precisely all of them are float.
¶
2.2 COMPUTATION AND VISUALIZATION OF MEAN, STD, QUANTILES, MAX, MIN, CORRELATION MATRIX
Now I want to compute and represent graphically the mean, std, quantiles, of the data points across their 25 features. In order to do so, I use the transposed of the dataset.
df_data_points_tr_summary = df_data_points_tr.describe()
df_data_points_tr_summary
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | ... | 1390 | 1391 | 1392 | 1393 | 1394 | 1395 | 1396 | 1397 | 1398 | 1399 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | ... | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 | 25.000000 |
| mean | 0.656437 | 0.245523 | 0.143659 | 0.280489 | 0.222108 | 0.193688 | -0.430322 | 0.283592 | -0.255867 | -0.687581 | ... | -0.100641 | -0.066638 | -0.014816 | 0.115674 | 1.128262 | 0.409728 | 0.681583 | 1.056996 | 0.575765 | -0.025159 |
| std | 3.019691 | 2.471941 | 2.401257 | 2.181782 | 2.428479 | 3.143410 | 2.265609 | 1.621682 | 2.123480 | 2.302009 | ... | 1.980072 | 1.803538 | 1.653497 | 1.468609 | 2.691906 | 2.049268 | 2.594289 | 3.091477 | 2.746377 | 1.426685 |
| min | -4.358051 | -4.999382 | -3.975294 | -2.559503 | -6.330675 | -6.634834 | -5.766030 | -3.084630 | -7.775547 | -5.468823 | ... | -6.728930 | -3.070705 | -2.884640 | -3.145130 | -2.924451 | -3.797807 | -5.258127 | -6.805083 | -5.569485 | -2.708364 |
| 25% | -0.576659 | -0.490495 | -1.009061 | -1.091440 | -0.396174 | -1.248468 | -1.703285 | -0.438854 | -0.721186 | -1.991403 | ... | -0.820145 | -1.729645 | -1.317473 | -0.624140 | -1.184189 | -0.608051 | -0.678494 | -0.706097 | -0.518803 | -1.156191 |
| 50% | 0.356847 | 0.527434 | 0.175052 | -0.113804 | 0.251268 | 0.037314 | -0.779006 | 0.464369 | 0.006886 | -0.045571 | ... | -0.142716 | -0.245327 | 0.278338 | -0.190353 | 0.932712 | 1.010512 | 1.063410 | 0.087376 | 0.444458 | -0.071741 |
| 75% | 0.880273 | 1.313825 | 0.905951 | 0.492805 | 1.710562 | 1.346645 | 1.085559 | 1.333070 | 0.468107 | 0.655720 | ... | 0.361732 | 1.083912 | 0.817680 | 0.720169 | 2.938863 | 1.423271 | 2.611102 | 3.372529 | 1.820581 | 0.516151 |
| max | 7.906497 | 4.609667 | 5.988060 | 5.601020 | 4.729981 | 9.718475 | 4.176352 | 4.117393 | 3.993937 | 4.407460 | ... | 5.272173 | 3.283793 | 4.801895 | 3.531062 | 8.763727 | 5.183851 | 6.019151 | 8.260052 | 6.574953 | 4.180642 |
8 rows × 1400 columns
I now plot the histogram of the counts of the mean, of the standard deviation and of the 75-percentile
sns.displot(df_data_points_tr_summary.iloc[1], bins=50, color='green')
plt.title("distribution of mean of data points")
plt.show()
sns.displot(df_data_points_tr_summary.iloc[2], bins=50, color='blue')
plt.title("distribution of std of data points")
plt.show()
sns.displot(df_data_points_tr_summary.iloc[6], bins=50, color='red')
plt.title("distribution of mean of data points")
plt.show()
As it is possible to notice, The histogram of the mean values across all features for each data point seems to follow a roughly normal distribution with majority of the values lying between -1 and 1.
For the other two plots:
- they exhibit a unimodal distribution, with the peak occurring between 2 and 3 for the standard deviation and between 1 and 2 for the 75th percentile;
- in the standard deviation plot, there is a right tail extending beyond 3, suggesting the presence of data points with higher variability, which could be outliers.
- in the 75th percentile plot, the right tail indicates the presence of some data points with higher values.
Also doing the reverse (see each features across all the data points) can help us.
df_data_points_summary = df_data_points.describe()
df_data_points_summary
| feature_1 | feature_2 | feature_3 | feature_4 | feature_5 | feature_6 | feature_7 | feature_8 | feature_9 | feature_10 | ... | feature_16 | feature_17 | feature_18 | feature_19 | feature_20 | feature_21 | feature_22 | feature_23 | feature_24 | feature_25 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | ... | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 | 1400.000000 |
| mean | 0.210835 | 0.612782 | -0.082197 | 0.185904 | 0.070735 | -0.359291 | -0.115731 | 0.210835 | 0.198517 | 0.050355 | ... | -0.099482 | 0.683999 | 0.109756 | 1.089425 | 0.018756 | 0.118668 | 0.079930 | -0.132304 | 1.543277 | 0.571845 |
| std | 2.195976 | 2.395809 | 2.358706 | 1.024291 | 2.418231 | 2.192464 | 2.295636 | 2.195976 | 2.305057 | 0.992986 | ... | 4.080395 | 2.303319 | 1.037643 | 4.646323 | 2.226349 | 1.017631 | 1.008222 | 2.360151 | 4.888676 | 2.287947 |
| min | -6.459859 | -7.795962 | -7.704676 | -2.948682 | -8.315868 | -7.448146 | -7.183413 | -6.459859 | -7.387299 | -4.282637 | ... | -15.063160 | -7.019747 | -3.042580 | -14.004747 | -6.790704 | -3.025071 | -3.247761 | -8.358437 | -15.669281 | -6.603355 |
| 25% | -1.350847 | -0.870054 | -1.739086 | -0.516367 | -1.465739 | -1.849062 | -1.747100 | -1.350847 | -1.347676 | -0.634657 | ... | -2.902051 | -0.868773 | -0.632218 | -2.030589 | -1.463973 | -0.555009 | -0.580996 | -1.643818 | -1.626720 | -0.823231 |
| 50% | 0.180684 | 0.673686 | -0.099358 | 0.200757 | 0.039412 | -0.356757 | -0.160878 | 0.180684 | 0.024433 | 0.051986 | ... | -0.170632 | 0.718832 | 0.107171 | 1.124641 | 0.043266 | 0.109773 | 0.110199 | -0.206132 | 1.608067 | 0.653977 |
| 75% | 1.768125 | 2.209933 | 1.563456 | 0.895352 | 1.709264 | 1.122682 | 1.347230 | 1.768125 | 1.651034 | 0.700098 | ... | 2.751130 | 2.251132 | 0.825007 | 4.141713 | 1.460704 | 0.752059 | 0.709252 | 1.444386 | 4.824556 | 2.188991 |
| max | 8.326302 | 7.934452 | 8.604717 | 3.300430 | 8.083031 | 6.043853 | 9.691771 | 8.326302 | 10.334941 | 4.228823 | ... | 14.220578 | 8.859061 | 3.351073 | 15.998109 | 8.324109 | 4.014849 | 3.563236 | 9.232769 | 19.603832 | 7.851396 |
8 rows × 25 columns
It is possible to notice that also the mean of each features across all data points seems approximately close to 0 and the variance low as well.
Plotting the distribution of each feature seems to tell us also that data has been normalized and is normally distributed.
df_data_points.hist(figsize=(10, 15), bins=30, color='blue')
plt.show()
Finally I plot the correlation matrix in order to see if I have some kind of correlation between features.
#plt.figure(figsize=(20, 15))
corr = df_data_points.corr()
sns.heatmap(corr,
xticklabels=corr.columns.values,
yticklabels=corr.columns.values)
plt.show()
As it is possible to notice most features are uncorrelated or little correlated. Of course it also pivotal to remember that the correlation coefficient captures linear relationship between features. So features have not linear correlation between themselves.
¶
2.3 ADDITIONAL CHECK TO SEE IF DATA IS NORMALIZED
I am going to analyze the skeweness and kurtosis for each single data point and for each feature in order to verify if data is normalized or not
# Skeweness of the data points
col_points = list(df_data_points_tr.columns)
colP = np.shape(df_data_points_tr)[1]
df_skew_c = []
for i in range(colP):
v_df = df_data_points_tr[col_points[i]]
df_skew_c += [skew(v_df)]
df_skew_c
sns.histplot(df_skew_c, bins=100, color='blue', kde=True)
plt.xlabel('Skeweness of data points')
plt.show()
# Skeweness of the features
col_points = list(df_data_points.columns)
colP = np.shape(df_data_points)[1]
df_skew_c = []
for i in range(colP):
v_df = df_data_points[col_points[i]]
df_skew_c += [skew(v_df)]
print(len(df_skew_c))
sns.histplot(df_skew_c, bins=100, color='orange')
plt.xlabel('Skeweness of features')
plt.show()
25
# Kurtosis of data points
col_points = list(df_data_points_tr.columns)
colP = np.shape(df_data_points_tr)[1]
df_kurt_c = []
for i in range(colP):
v_df = df_data_points_tr[col_points[i]]
df_kurt_c += [kurtosis(v_df)]
df_kurt_c
sns.histplot(df_kurt_c, bins=100, color='purple', kde=True)
plt.xlabel('Kurtosis of data points')
plt.show()
# Kurtosis of features
col_points = list(df_data_points.columns)
colP = np.shape(df_data_points)[1]
df_kurt_c = []
for i in range(colP):
v_df = df_data_points[col_points[i]]
df_kurt_c += [kurtosis(v_df)]
print(len(df_kurt_c))
sns.histplot(df_kurt_c, bins=100, color='purple')
plt.xlabel('Kurtosis of data points')
plt.show()
25
It is possible to see that the skewness is close to 0, since most values are between -1 and 1, with some exception regarding the data points plot where I have some points that overcome 2 or -2.
The Kurtosis has bigger values, but most of the data is still near 0 (or between the interval -1 and 2) with couple of examples having larger values. This tells us that the distribution of the data is close to the one of a normal distribution.
¶
2.4 CHECK IF CLASSES ARE BALANCED
I now want to check how the classes are distributed across the samples, in order to understand if I am going to train the models with a potential bias (for example if I have a class that appears more, my model will be trained with more data about this class and could develop a sort of bias)
print(labels_t.value_counts())
labels_t.value_counts().plot.pie(autopct='%.2f')
label 0 295 4 290 1 274 3 271 2 270 Name: count, dtype: int64
<Axes: ylabel='count'>
As it is possible to notice all the classes seem to appear almost the same number of time:
- 295 data points have class 0 (21.07%)
- 274 data points have class 1 (19.57%)
- 270 data points have class 2 (19.29%)
- 271 data points have class 3 (19.36%)
- 290 data points have class 4 (20.71%)
¶
- UNSUPERVISED LEARNING METHODS
Now I am going to apply some unsupervised learning models to our dataset in order to further explore it.
In particular, I am going to apply PCA, which transforms high-dimensional data into a lower-dimensional representation while preserving the most important information by identifying the directions of maximum variance in the data.
pca = PCA()
df_pca = pca.fit_transform(df_data_points)
cumulative_sum = np.cumsum(pca.explained_variance_ratio_)
plt.figure(figsize=(10, 4))
# plot 1
plt.subplot(1, 2, 1)
plt.title("Cumulative Variance")
plt.plot(cumulative_sum)
plt.xlabel("Component")
plt.ylabel("Explained Variance (%)")
plt.grid(True)
# plot 2
plt.subplot(1, 2, 2)
plt.title("Explained Variance per Component")
plt.plot(pca.explained_variance_ratio_)
plt.ylabel("Explained Variance (%)")
plt.xlabel('Component')
plt.grid(True)
plt.tight_layout()
plt.show()
The cumulative variance plot shows a rapid increase initially and then a plateau, indicating that a few principal components explain most of the variance in the data.
The elbow point seems to be at around the 5th or 6th component supporting the idea of selecting these many components for effective dimensionality reduction.
I now plot it in 2 and 3 dimensions to see if any interesting structures emerges.
# Plot 2D and 3D visualizations
labels = df["label"]
fig = plt.figure(figsize=(14, 7))
# 2D Plot
ax_2d = fig.add_subplot(121)
scatter_2d = ax_2d.scatter(df_pca[:, 0], df_pca[:, 1], c=labels)
ax_2d.set_xlabel("PCA1")
ax_2d.set_ylabel("PCA2")
ax_2d.set_title(f"Explained Variance: {round(pca.explained_variance_ratio_[0] + pca.explained_variance_ratio_[1], 2)}")
# 3D Plot
ax_3d = fig.add_subplot(122, projection='3d')
scatter_3d = ax_3d.scatter(df_pca[:, 0], df_pca[:, 1], df_pca[:, 2], c=labels)
ax_3d.set_xlabel("PCA1")
ax_3d.set_ylabel("PCA2")
ax_3d.set_zlabel("PCA3")
ax_3d.set_title(f"Explained Variance: {round(pca.explained_variance_ratio_[0] + pca.explained_variance_ratio_[1] + pca.explained_variance_ratio_[2], 2)}")
# Add legend
handles, legend_labels = scatter_2d.legend_elements()
ax_3d.legend(handles, legend_labels, loc='best', title='Classes')
plt.suptitle("PCA Visualization")
plt.tight_layout()
plt.show()
As it is possible to notice there is no real separation between classes, they are all mixed and there are no clear patterns between them.
¶
- CLASSIFIERS
I now start splitting the original dataset into training and test set. This split will be pivotal for the model I will need to work with.
print(df_data_points.shape, df_labels.shape)
X_train, X_test, y_train, y_test = train_test_split(df_data_points, df_labels, test_size=0.2, random_state=42)
print(X_train.shape, y_train.shape)
print(X_test.shape, y_test.shape )
(1400, 25) (1400,) (1120, 25) (1120,) (280, 25) (280,)
¶
4.1 RANDOM FOREST
¶
4.1.1 SIMPLE RANDOM FOREST
I start applying the simplest random forest (no search of best parameters, no cross validation) to our dataset with an initial number of estimators of 100.
rfc= RandomForestClassifier(random_state=42, n_jobs=-1,
n_estimators=100)
rfc.fit(X_train,y_train)
RandomForestClassifier(n_jobs=-1, random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomForestClassifier(n_jobs=-1, random_state=42)
y_pred = rfc.predict(X_test)
accuracy_score(y_pred, y_test)
0.6642857142857143
As it is possible to notice I get the accuracy around the 66%, so it is not very good.
Therefore I am going to tune the parameters in order to see if something changes.
¶
4.1.2 RANDOM FOREST WITH GRID SEARCH
Now I have decided to use a Random Forest classifier with a Grid Search to find the best hyperparameters. I consider as hyperparameters that have a huge impact on our random forest the depth, the number of estimators (trees) and the criterion used.
Since it is impractical to explore all possible combinations due to time and computational constraints, I have selected a subset of hyperparameters for the grid search.
In particular:
- for the number of estimators which specifies the number of trees in the forest I chose values of 1000, 1200, and 1400. These values are significantly larger than the 100 estimators used before, aiming to improve the model's performance while not being excessively large to avoid overfitting.
- for the criterion which determines the function to measure the quality of a split I chose 'gini' (Gini impurity) and 'entropy' (Information gain), which are the two most commonly used criteria in Random Forests.
- for max_depth which specifies the maximum depth of the tree I included values 10, 20, and None ('None' means that nodes are expanded until all leaves contain less than min_samples_split samples).
Finally for the grid configuration I used 5-fold cross-validation ( I tried to slightly vary this number, e.g with 3 or 6, but the results were almost similar).
rf = RandomForestClassifier(n_jobs=-1, random_state=42)
parameters = {
'max_depth': [10, 20, None],
'criterion': ['gini', 'entropy'],
'n_estimators': [1000, 1200, 1400]
}
grid_search = GridSearchCV(estimator=rf,
param_grid=parameters,
cv = 5,
n_jobs = -1, verbose=1,
scoring='accuracy')
grid_search.fit(X_train, y_train)
Fitting 5 folds for each of 18 candidates, totalling 90 fits
GridSearchCV(cv=5, estimator=RandomForestClassifier(n_jobs=-1, random_state=42),
n_jobs=-1,
param_grid={'criterion': ['gini', 'entropy'],
'max_depth': [10, 20, None],
'n_estimators': [1000, 1200, 1400]},
scoring='accuracy', verbose=1)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
GridSearchCV(cv=5, estimator=RandomForestClassifier(n_jobs=-1, random_state=42),
n_jobs=-1,
param_grid={'criterion': ['gini', 'entropy'],
'max_depth': [10, 20, None],
'n_estimators': [1000, 1200, 1400]},
scoring='accuracy', verbose=1)RandomForestClassifier(n_jobs=-1, random_state=42)
RandomForestClassifier(n_jobs=-1, random_state=42)
rf_best = grid_search.best_estimator_
rf_best
RandomForestClassifier(criterion='entropy', max_depth=20, n_estimators=1000,
n_jobs=-1, random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomForestClassifier(criterion='entropy', max_depth=20, n_estimators=1000,
n_jobs=-1, random_state=42)y_pred_grid = rf_best.predict(X_test)
accuracy_score(y_pred_grid, y_test)
0.7142857142857143
So it is possible to see that the best model from the grid search has an accuracy of 71.42%. Despite it is still not incredibly high, it is better then the one of before (almost 66.4%).
I now represent graphically the confusion matrix which gives in details the distribution of the prediction (in the sense that it is possible to see how many right prediction the model gets for each class and also the wrong prediction for each class and what class was instead chosen). So it is very useful to have a precise idea on how the predictions happened.
cf_matrix_rf_grid = confusion_matrix(y_test, y_pred_grid)
cf_matrix_rf_grid
array([[50, 4, 3, 3, 5],
[ 4, 40, 2, 5, 1],
[ 9, 1, 37, 5, 3],
[ 8, 5, 0, 40, 3],
[ 4, 5, 8, 2, 33]])
#plt.figure(figsize=(10, 7))
plt.imshow(cf_matrix_rf_grid, interpolation='nearest', cmap='Blues')
plt.title('Confusion Matrix for Random Forest with Grid Search')
plt.colorbar()
# Draw the grid boxes
class_names = ['0', '1', '2', '3', '4']
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# Draw the text boxes
thresh = cf_matrix_rf_grid.max() / 2.
for i, j in itertools.product(range(cf_matrix_rf_grid.shape[0]), range(cf_matrix_rf_grid.shape[1])):
plt.text(j, i, cf_matrix_rf_grid[i, j],
horizontalalignment="center",
color="white" if cf_matrix_rf_grid[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
From the confusion matrix it is possible to notice that the random forest predicted wrong 21 data points as class 0, 15 as class 1, 14 as class 2, 12 as class 3 and 18 data points as class 4. So the most probablematic were false 0 and false 4. But this makes sense also because class 0 and class 4 were the most represented classes in the dataset (it is important to notice that this is a very small difference but it was nice to be pointed out).
I now try to implement a random forest with a random search to see if something changes.
¶
4.1.3 RANDOM FOREST WITH RANDOM SEARCH
I now try to tune the parameters with a Random Grid Search, in order to see if I can get a similar or better accuracy. Basically the goal of the random search is the one of finding the best hyperparameters for our classifier (random forest), but instead of trying combining all the parameters (as done before), it randomly combine them and choose the one with the best performance. It is useful especially in situations where we have a large number of combinations (with the con that it may leave out some of the best combinations).
In particular I choose the following parameters for the random grid (some of them are new compared to the hyperparameters used in grid search since I wanted to explore also other aspects and take advantage of the random factor):
- for the number of estimators I chose a range of values from 200 to 2000, sampled at 10 evenly spaced intervals. These values are intended to find the optimal balance between model performance and the risk of overfitting;
- for the criterion I chose 'gini' (Gini impurity) and 'entropy' (Information gain).
- for the maximum features which defines the number of features to consider when looking for the best split, I used 'auto' (all features), 'sqrt' (square root of the number of features), and 'log2' (log base 2 of the number of features), which are common choices for Random Forests.
- for the minimum samples split and for the minimum samples leaf (it defines the minimum number of samples required to be at a leaf node) I chose respectively values 2, 5, and 10 and values 1, 2, 4, and 10 (I prefer to keep smaller values in order to make my random forest as much flexible as possible)
- I consider bootstrapping as well (so if sample or not just some features).
Moreover, in this case I chose just 3 cross validation and 500 number of iterations due to the computational cost.
# number of trees in the random forest
n_estimators = [int(x) for x in np.linspace(start=200, stop=2000, num=10)]
# number of features to consider at every split
max_features = ['auto', 'sqrt', 'log2']
# depth at which stops
#max_depth = [None, 10, 20, 30]
# minimum number of samples required to split a node
min_samples_split = [2, 5, 10]
# minimum number of samples required at each leaf node
min_samples_leaf = [1, 2, 4, 10]
# Method of selecting samples for training each tree
bootstrap = [True, False]
# Random Grid
random_grid = {'n_estimators': n_estimators,
'max_features': max_features,
'criterion': ['gini', 'entropy'],
#'max_depth': max_depth,
'min_samples_split': min_samples_split,
'min_samples_leaf': min_samples_leaf,
'bootstrap': bootstrap}
print(random_grid)
{'n_estimators': [200, 400, 600, 800, 1000, 1200, 1400, 1600, 1800, 2000], 'max_features': ['auto', 'sqrt', 'log2'], 'criterion': ['gini', 'entropy'], 'min_samples_split': [2, 5, 10], 'min_samples_leaf': [1, 2, 4, 10], 'bootstrap': [True, False]}
# I use the random grid now to search for the best hyperparameters
rf_rgrid = RandomForestClassifier()
# Random search of parameters, using 3 fold cross validation,
# search across 100 different combinations, and use all available cores
rf_random = RandomizedSearchCV(estimator = rf_rgrid, param_distributions = random_grid, n_iter = 500, cv = 3, verbose=2, random_state=12, n_jobs = -1)
# Finally I fit the random search model
rf_random.fit(X_train, y_train)
Fitting 3 folds for each of 500 candidates, totalling 1500 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 6.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 5.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 5.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 10.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 11.2s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 11.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 6.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 6.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 6.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 10.2s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 10.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 8.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 10.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 4.2s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 8.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 8.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 4.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 6.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 6.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 12.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 6.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 11.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 11.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 4.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 4.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 4.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=2000; total time= 7.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=2000; total time= 7.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 4.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=2000; total time= 8.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 3.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 3.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 8.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 6.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 6.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 6.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 9.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 9.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 4.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 4.2s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 2.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 2.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 4.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 2.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 2.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.7s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 6.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 6.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 8.6s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 9.2s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 9.2s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 8.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 9.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 10.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 8.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 10.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 10.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 3.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 3.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 7.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 7.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=600; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=600; total time= 1.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=600; total time= 1.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 7.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 3.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 8.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 8.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 8.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 2.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 3.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 4.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 4.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 5.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 5.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 3.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 3.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 3.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 3.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 3.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 3.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 2.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 4.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 4.2s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 4.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 1.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 7.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 8.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 8.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 5.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 5.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 5.0s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 3.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 10.8s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 4.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 11.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 10.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 1.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 9.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 9.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 9.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 5.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 3.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 5.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 3.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.8s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 3.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 2.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 2.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 3.0s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 5.5s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 5.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 5.7s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 8.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 2.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 8.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 8.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 1.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 1.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 2.4s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 4.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 5.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 2.4s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 4.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 2.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 2.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 2.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 6.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 3.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 6.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 1.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 7.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 4.2s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 1.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 12.2s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 12.1s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 12.0s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 2.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 1.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 1.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 5.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 8.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 8.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 8.7s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 5.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 5.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 4.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 4.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 4.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=2000; total time= 5.7s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=2000; total time= 5.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=2000; total time= 5.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 6.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1600; total time= 4.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 6.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.4s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 6.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1600; total time= 4.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1600; total time= 4.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 2.2s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 3.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 5.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 3.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 5.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 4.2s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 10.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 10.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 2.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 10.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 3.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 3.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 3.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 5.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 5.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 5.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.2s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 2.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 3.2s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 3.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 7.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 7.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 3.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 7.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 3.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 5.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 9.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 9.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 3.4s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 9.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 4.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 4.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 5.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 5.2s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 5.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 5.7s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 5.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 6.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 3.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 3.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 3.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 5.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 5.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 4.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 4.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1000; total time= 4.9s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 4.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 4.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 4.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 5.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 6.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 6.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 3.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 7.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 3.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 3.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 7.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 7.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 5.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 8.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 8.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 8.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 5.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 7.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 6.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 7.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 7.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 7.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 7.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 2.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 2.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 2.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 5.2s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 5.2s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 5.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 10.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 5.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 10.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 5.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 10.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 3.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 3.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 3.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 8.5s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 1.7s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 1.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 8.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=600; total time= 1.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 5.4s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 5.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 8.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.3s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.9s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 7.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 8.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 8.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 7.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 7.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 2.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 3.0s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 8.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1000; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 4.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 4.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 5.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 5.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 5.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.5s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 5.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 5.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 5.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 5.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 5.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 5.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 5.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 5.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 5.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 4.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 5.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 3.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 5.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 3.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 2.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 2.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.2s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 8.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 8.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 9.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 4.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 6.2s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 6.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 6.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 9.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 9.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 9.1s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 2.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 2.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 2.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 1.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 2.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 1.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 2.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 6.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 1.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 6.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 7.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 2.8s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 2.8s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 2.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 7.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 7.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 7.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 1.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 6.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 6.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 6.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 4.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 1.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 1.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 4.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 4.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 9.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 9.7s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 9.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 1.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 4.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 4.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 4.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 4.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 4.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 4.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 2.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 6.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 6.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 6.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 1.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 3.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 3.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 7.4s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 3.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 7.7s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 7.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 3.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 3.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 3.5s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 5.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 5.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 7.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1000; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 3.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 3.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 7.6s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 3.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 7.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 2.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 2.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 4.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 5.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 1.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 5.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 3.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 3.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 3.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 5.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 1.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 1.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 7.6s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 7.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 7.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 1.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 1.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 1.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 2.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 3.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 3.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 3.4s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 4.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 5.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 9.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 9.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 10.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 6.2s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 4.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 6.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 6.2s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 4.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 4.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 3.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 3.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 4.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 4.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 11.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 11.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 11.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 6.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 6.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 6.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.7s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 4.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 5.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 5.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 5.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 2.0s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 1.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 2.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 5.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 5.3s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 5.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 6.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 6.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 6.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 5.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 4.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 6.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 6.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 4.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 4.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 5.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 5.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=800; total time= 5.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 7.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 7.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 7.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 7.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 8.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 7.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 9.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 3.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 3.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 9.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 6.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 9.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 7.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 3.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 6.8s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 3.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 3.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 6.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 6.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1600; total time= 6.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 4.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 4.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 4.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 4.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 4.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1400; total time= 4.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 6.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 6.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 6.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 4.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 5.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 4.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 5.0s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 0.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1800; total time= 4.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 6.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 6.4s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 0.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 6.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=200; total time= 0.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 1.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 1.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=600; total time= 1.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.3s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 5.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1400; total time= 5.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1400; total time= 5.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1400; total time= 5.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 1.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 1.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 1.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 7.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 7.3s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 7.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 5.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 3.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 5.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 5.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 3.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=1600; total time= 3.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 7.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 7.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 7.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 1.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 7.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 7.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 7.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 1.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=800; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 4.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=200; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 1.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 8.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 8.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 3.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 3.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 8.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 3.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 1.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 1.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 3.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 1.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 2.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 3.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 3.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 3.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 2.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 5.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 5.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1000; total time= 5.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 6.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 7.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 7.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 2.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 2.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 7.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 7.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 4.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 2.4s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 2.3s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 4.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 7.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 4.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=600; total time= 2.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=400; total time= 0.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 6.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 4.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 6.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 4.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 6.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=800; total time= 4.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 7.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 7.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 7.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 4.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 4.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 4.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 1.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 10.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 10.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 10.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 5.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 5.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 6.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1400; total time= 4.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1400; total time= 4.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1400; total time= 6.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1400; total time= 4.0s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1400; total time= 5.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 4.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 4.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1400; total time= 5.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 4.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 4.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 4.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1800; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1400; total time= 6.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1400; total time= 6.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1400; total time= 5.8s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 5.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 11.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 11.7s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 12.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 12.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 12.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1800; total time= 12.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 13.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 13.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 14.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 8.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 6.1s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 8.7s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 8.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.5s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 6.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 6.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 4.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 1.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 3.2s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 1.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 6.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 6.8s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1800; total time= 6.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 2.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 2.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 2.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 5.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 5.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 5.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 5.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 5.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 5.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 6.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 6.0s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 4.2s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 4.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 6.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 2.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=600; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 2.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 8.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 8.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 8.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 5.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 5.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 5.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 5.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 12.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 12.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=2000; total time= 13.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 2.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 13.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 12.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 5.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 3.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 12.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 4.2s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 4.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 0.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 4.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 4.3s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 4.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 1.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 1.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=400; total time= 1.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1200; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1200; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1200; total time= 5.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1200; total time= 4.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1200; total time= 4.0s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 3.2s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1200; total time= 4.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 7.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 3.3s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 7.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 3.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 10.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=1800; total time= 8.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 10.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 10.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 1.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 1.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=600; total time= 1.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 6.3s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 6.4s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1000; total time= 6.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 4.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 4.6s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 3.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 5.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1600; total time= 5.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 3.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 3.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 3.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 2.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 4.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=600; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=800; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=600; total time= 2.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=600; total time= 2.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 4.2s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.6s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 5.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 4.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1600; total time= 4.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 5.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1400; total time= 5.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=800; total time= 3.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 8.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 8.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1600; total time= 8.5s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 4.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 4.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 4.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1000; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1000; total time= 2.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1000; total time= 2.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1200; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 6.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 6.2s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1800; total time= 6.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 8.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 8.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 3.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 8.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 3.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 7.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 7.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 8.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1000; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 1.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=600; total time= 3.4s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=600; total time= 3.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 2.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=600; total time= 3.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 2.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 2.2s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.2s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 8.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 8.0s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 8.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 5.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 7.2s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 7.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 7.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 5.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=400; total time= 1.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1800; total time= 5.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.2s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 3.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 3.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1000; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 12.3s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 12.5s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=2000; total time= 12.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 6.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 5.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 6.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1800; total time= 6.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 5.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 3.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1600; total time= 6.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1400; total time= 3.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=800; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 5.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 2.6s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=400; total time= 2.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 5.6s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 5.7s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=600; total time= 1.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=600; total time= 1.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 0.5s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=600; total time= 1.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.6s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 2.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 4.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 4.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 4.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1600; total time= 7.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1600; total time= 7.4s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 2.3s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1600; total time= 7.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 3.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 3.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 3.5s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 3.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=1000; total time= 3.7s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 3.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 6.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 7.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 7.5s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=2000; total time= 8.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 6.5s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 6.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 6.3s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 6.5s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.9s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1600; total time= 6.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.2s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=800; total time= 2.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=800; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 0.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 2.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1000; total time= 2.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 7.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 7.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=5, n_estimators=2000; total time= 7.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 6.3s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 4.6s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 6.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1800; total time= 6.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 1.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 4.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1200; total time= 4.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=400; total time= 1.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 9.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 3.6s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 9.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 9.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 4.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 4.3s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 5.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 5.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=5, n_estimators=800; total time= 5.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 7.8s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 7.7s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 7.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.9s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 8.3s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 6.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 2.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=800; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.8s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=400; total time= 1.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 8.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.2s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 8.8s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 7.0s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 7.0s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 4.3s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 5.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 5.9s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 4.6s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1600; total time= 4.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 6.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 6.1s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 6.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 6.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 1.1s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 1.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=200; total time= 1.2s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.8s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=5, n_estimators=200; total time= 0.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 3.8s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1600; total time= 3.8s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 5.0s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.1s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 5.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=600; total time= 2.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 4.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 4.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.6s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1200; total time= 4.5s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 1.9s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=400; total time= 2.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1400; total time= 8.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1400; total time= 8.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=5, n_estimators=1400; total time= 8.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 4.4s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 6.6s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 4.4s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 4.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 6.7s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=10, n_estimators=2000; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 6.9s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 3.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 2.9s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 3.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=400; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1000; total time= 3.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 7.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 7.5s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=400; total time= 2.7s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=400; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 7.3s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=1200; total time= 3.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 5.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 5.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1600; total time= 5.2s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 7.4s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 7.5s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=2000; total time= 7.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 4.7s [CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 4.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 7.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=1400; total time= 4.9s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=600; total time= 2.4s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=600; total time= 2.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 6.7s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 8.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=2000; total time= 8.1s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 6.8s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1000; total time= 6.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 6.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 6.5s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 5.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 5.1s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=4, min_samples_split=10, n_estimators=200; total time= 0.7s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=5, n_estimators=2000; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1400; total time= 5.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 6.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1400; total time= 5.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=1400; total time= 5.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 4.1s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 4.3s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.4s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.4s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1400; total time= 4.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 1.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=600; total time= 1.5s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.2s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=400; total time= 1.2s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 3.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=1200; total time= 3.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.1s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.0s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=4, min_samples_split=10, n_estimators=800; total time= 2.2s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.5s [CV] END bootstrap=True, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=400; total time= 1.7s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1200; total time= 3.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 11.5s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 11.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.0s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 4.0s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=4, min_samples_split=2, n_estimators=2000; total time= 12.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 1.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=400; total time= 0.9s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 6.1s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 6.6s [CV] END bootstrap=False, criterion=entropy, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1200; total time= 6.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 4.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=5, n_estimators=1400; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 2.6s [CV] END bootstrap=True, criterion=gini, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1400; total time= 2.7s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 3.1s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 3.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 3.1s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 3.8s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=5, n_estimators=1800; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 3.7s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=600; total time= 3.8s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=400; total time= 1.4s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=400; total time= 1.3s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=400; total time= 1.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 6.4s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 6.3s [CV] END bootstrap=False, criterion=gini, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1600; total time= 6.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 5.6s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 5.4s [CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 3.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 3.0s [CV] END bootstrap=True, criterion=entropy, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1200; total time= 5.3s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, criterion=gini, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1400; total time= 2.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 3.8s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 3.9s [CV] END bootstrap=True, criterion=gini, max_features=auto, min_samples_leaf=2, min_samples_split=10, n_estimators=1400; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.9s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.8s [CV] END bootstrap=False, criterion=entropy, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=600; total time= 3.8s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 3.4s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 3.0s [CV] END bootstrap=True, criterion=entropy, max_features=log2, min_samples_leaf=10, min_samples_split=5, n_estimators=1200; total time= 3.0s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 3.1s [CV] END bootstrap=False, criterion=gini, max_features=log2, min_samples_leaf=2, min_samples_split=10, n_estimators=1200; total time= 3.1s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 10.0s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 10.2s [CV] END bootstrap=False, criterion=entropy, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=1800; total time= 10.5s
RandomizedSearchCV(cv=3, estimator=RandomForestClassifier(), n_iter=500,
n_jobs=-1,
param_distributions={'bootstrap': [True, False],
'criterion': ['gini', 'entropy'],
'max_features': ['auto', 'sqrt',
'log2'],
'min_samples_leaf': [1, 2, 4, 10],
'min_samples_split': [2, 5, 10],
'n_estimators': [200, 400, 600, 800,
1000, 1200, 1400, 1600,
1800, 2000]},
random_state=12, verbose=2)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomizedSearchCV(cv=3, estimator=RandomForestClassifier(), n_iter=500,
n_jobs=-1,
param_distributions={'bootstrap': [True, False],
'criterion': ['gini', 'entropy'],
'max_features': ['auto', 'sqrt',
'log2'],
'min_samples_leaf': [1, 2, 4, 10],
'min_samples_split': [2, 5, 10],
'n_estimators': [200, 400, 600, 800,
1000, 1200, 1400, 1600,
1800, 2000]},
random_state=12, verbose=2)RandomForestClassifier()
RandomForestClassifier()
rf_random.best_params_
{'n_estimators': 1200,
'min_samples_split': 2,
'min_samples_leaf': 1,
'max_features': 'log2',
'criterion': 'gini',
'bootstrap': False}
best_random_est = rf_random.best_estimator_
best_random_est
RandomForestClassifier(bootstrap=False, max_features='log2', n_estimators=1200)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomForestClassifier(bootstrap=False, max_features='log2', n_estimators=1200)
best_random_est.fit(X_train, y_train)
RandomForestClassifier(bootstrap=False, max_features='log2', n_estimators=1200)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomForestClassifier(bootstrap=False, max_features='log2', n_estimators=1200)
y_pred_g_random = best_random_est.predict(X_test)
accuracy_score(y_pred_g_random, y_test)
0.7285714285714285
The accuracy of the best random forest model from the random search is approximately of 72.8% so a little bit higher then the one of the grid search. Still, it is not very satisfying.
I am now going to represent the confusion matrix for this classifier.
cf_matrix_rf_random = confusion_matrix(y_test, y_pred_g_random)
cf_matrix_rf_random
array([[51, 4, 3, 2, 5],
[ 2, 40, 2, 6, 2],
[ 5, 1, 40, 3, 6],
[ 8, 4, 0, 40, 4],
[ 3, 5, 7, 2, 35]])
plt.imshow(cf_matrix_rf_random, interpolation='nearest', cmap='Blues')
plt.title('Confusion Matrix for Random Forest with Random Search')
plt.colorbar()
# Draw the grid boxes
class_names = ['0', '1', '2', '3', '4']
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# Draw the text boxes
thresh = cf_matrix_rf_random.max() / 2.
for i, j in itertools.product(range(cf_matrix_rf_random.shape[0]), range(cf_matrix_rf_random.shape[1])):
plt.text(j, i, cf_matrix_rf_random[i, j],
horizontalalignment="center",
color="white" if cf_matrix_rf_random[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
¶
4.1.4 RANDOM FOREST WITH BAYESIAN SEARCH
Here I use a Random Forest classifier with Bayesian Search to find the best hyperparameters. It is an advanced method for hyperparameter tuning that builds a probabilistic model of the function mapping hyperparameters to a performance metric. It uses this model to select the most promising hyperparameters to evaluate next, aiming to find the best hyperparameters more efficiently than random or grid search.
In this case, I initialized the search space with similar parameters as before (without specifying in this case the criterion) adding the maximum depth parameter. Moreover I consider 3 cross validation and just 100 number of iterations.
# Define the search space
search_space = {
'n_estimators': Integer(200, 2000),
'max_features': Categorical(['auto', 'sqrt', 'log2']),
'max_depth': Integer(10, 110),
'min_samples_split': Integer(2, 10),
'min_samples_leaf': Integer(1, 10),
'bootstrap': Categorical([True, False])
}
# Initialize the model
rf_b = RandomForestClassifier(random_state=42)
# Bayesian search
bayes_search = BayesSearchCV(
estimator=rf_b,
search_spaces=search_space,
n_iter=100,
cv=3,
n_jobs=-1,
verbose=2,
random_state=42
)
# Fit the Bayesian search
bayes_search.fit(X_train, y_train)
Fitting 3 folds for each of 1 candidates, totalling 3 fits
[CV] END bootstrap=True, max_depth=83, max_features=log2, min_samples_leaf=4, min_samples_split=7, n_estimators=945; total time= 1.8s [CV] END bootstrap=True, max_depth=83, max_features=log2, min_samples_leaf=4, min_samples_split=7, n_estimators=945; total time= 1.8s [CV] END bootstrap=True, max_depth=83, max_features=log2, min_samples_leaf=4, min_samples_split=7, n_estimators=945; total time= 1.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=98, max_features=auto, min_samples_leaf=10, min_samples_split=9, n_estimators=312; total time= 0.8s [CV] END bootstrap=False, max_depth=98, max_features=auto, min_samples_leaf=10, min_samples_split=9, n_estimators=312; total time= 0.8s [CV] END bootstrap=False, max_depth=98, max_features=auto, min_samples_leaf=10, min_samples_split=9, n_estimators=312; total time= 0.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=102, max_features=auto, min_samples_leaf=5, min_samples_split=4, n_estimators=1017; total time= 2.1s [CV] END bootstrap=True, max_depth=102, max_features=auto, min_samples_leaf=5, min_samples_split=4, n_estimators=1017; total time= 2.2s [CV] END bootstrap=True, max_depth=102, max_features=auto, min_samples_leaf=5, min_samples_split=4, n_estimators=1017; total time= 2.1s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=27, max_features=sqrt, min_samples_leaf=8, min_samples_split=6, n_estimators=372; total time= 1.0s [CV] END bootstrap=False, max_depth=27, max_features=sqrt, min_samples_leaf=8, min_samples_split=6, n_estimators=372; total time= 1.0s [CV] END bootstrap=False, max_depth=27, max_features=sqrt, min_samples_leaf=8, min_samples_split=6, n_estimators=372; total time= 0.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=54, max_features=sqrt, min_samples_leaf=7, min_samples_split=9, n_estimators=1491; total time= 3.9s [CV] END bootstrap=False, max_depth=54, max_features=sqrt, min_samples_leaf=7, min_samples_split=9, n_estimators=1491; total time= 3.9s [CV] END bootstrap=False, max_depth=54, max_features=sqrt, min_samples_leaf=7, min_samples_split=9, n_estimators=1491; total time= 4.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=104, max_features=auto, min_samples_leaf=3, min_samples_split=8, n_estimators=871; total time= 2.6s [CV] END bootstrap=False, max_depth=104, max_features=auto, min_samples_leaf=3, min_samples_split=8, n_estimators=871; total time= 2.6s [CV] END bootstrap=False, max_depth=104, max_features=auto, min_samples_leaf=3, min_samples_split=8, n_estimators=871; total time= 2.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=88, max_features=sqrt, min_samples_leaf=9, min_samples_split=7, n_estimators=1270; total time= 3.2s [CV] END bootstrap=False, max_depth=88, max_features=sqrt, min_samples_leaf=9, min_samples_split=7, n_estimators=1270; total time= 3.2s [CV] END bootstrap=False, max_depth=88, max_features=sqrt, min_samples_leaf=9, min_samples_split=7, n_estimators=1270; total time= 3.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=102, max_features=sqrt, min_samples_leaf=9, min_samples_split=5, n_estimators=292; total time= 0.7s [CV] END bootstrap=False, max_depth=102, max_features=sqrt, min_samples_leaf=9, min_samples_split=5, n_estimators=292; total time= 0.7s [CV] END bootstrap=False, max_depth=102, max_features=sqrt, min_samples_leaf=9, min_samples_split=5, n_estimators=292; total time= 0.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=80, max_features=log2, min_samples_leaf=5, min_samples_split=5, n_estimators=581; total time= 1.4s [CV] END bootstrap=False, max_depth=80, max_features=log2, min_samples_leaf=5, min_samples_split=5, n_estimators=581; total time= 1.4s [CV] END bootstrap=False, max_depth=80, max_features=log2, min_samples_leaf=5, min_samples_split=5, n_estimators=581; total time= 1.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=92, max_features=log2, min_samples_leaf=3, min_samples_split=7, n_estimators=694; total time= 1.4s [CV] END bootstrap=True, max_depth=92, max_features=log2, min_samples_leaf=3, min_samples_split=7, n_estimators=694; total time= 1.4s [CV] END bootstrap=True, max_depth=92, max_features=log2, min_samples_leaf=3, min_samples_split=7, n_estimators=694; total time= 1.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=105, max_features=auto, min_samples_leaf=1, min_samples_split=9, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, max_depth=105, max_features=auto, min_samples_leaf=1, min_samples_split=9, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, max_depth=105, max_features=auto, min_samples_leaf=1, min_samples_split=9, n_estimators=200; total time= 0.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=64, max_features=log2, min_samples_leaf=2, min_samples_split=8, n_estimators=2000; total time= 4.0s [CV] END bootstrap=True, max_depth=64, max_features=log2, min_samples_leaf=2, min_samples_split=8, n_estimators=2000; total time= 4.0s [CV] END bootstrap=True, max_depth=64, max_features=log2, min_samples_leaf=2, min_samples_split=8, n_estimators=2000; total time= 4.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=53, max_features=sqrt, min_samples_leaf=2, min_samples_split=3, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, max_depth=53, max_features=sqrt, min_samples_leaf=2, min_samples_split=3, n_estimators=200; total time= 0.6s [CV] END bootstrap=False, max_depth=53, max_features=sqrt, min_samples_leaf=2, min_samples_split=3, n_estimators=200; total time= 0.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=102, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=1983; total time= 6.6s [CV] END bootstrap=False, max_depth=102, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=1983; total time= 6.6s [CV] END bootstrap=False, max_depth=102, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=1983; total time= 6.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=794; total time= 2.0s [CV] END bootstrap=True, max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=794; total time= 2.0s [CV] END bootstrap=True, max_depth=15, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=794; total time= 2.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=83, max_features=log2, min_samples_leaf=3, min_samples_split=2, n_estimators=1736; total time= 4.5s [CV] END bootstrap=False, max_depth=83, max_features=log2, min_samples_leaf=3, min_samples_split=2, n_estimators=1736; total time= 4.5s [CV] END bootstrap=False, max_depth=83, max_features=log2, min_samples_leaf=3, min_samples_split=2, n_estimators=1736; total time= 4.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.4s [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.4s [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=50, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1928; total time= 4.5s [CV] END bootstrap=True, max_depth=50, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1928; total time= 4.6s [CV] END bootstrap=True, max_depth=50, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1928; total time= 4.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=110, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.8s [CV] END bootstrap=False, max_depth=110, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.8s [CV] END bootstrap=False, max_depth=110, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=14, max_features=log2, min_samples_leaf=6, min_samples_split=2, n_estimators=1459; total time= 3.4s [CV] END bootstrap=False, max_depth=14, max_features=log2, min_samples_leaf=6, min_samples_split=2, n_estimators=1459; total time= 3.4s [CV] END bootstrap=False, max_depth=14, max_features=log2, min_samples_leaf=6, min_samples_split=2, n_estimators=1459; total time= 3.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 0.7s [CV] END bootstrap=False, max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=200; total time= 0.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=59, max_features=auto, min_samples_leaf=3, min_samples_split=2, n_estimators=242; total time= 0.7s [CV] END bootstrap=False, max_depth=59, max_features=auto, min_samples_leaf=3, min_samples_split=2, n_estimators=242; total time= 0.8s [CV] END bootstrap=False, max_depth=59, max_features=auto, min_samples_leaf=3, min_samples_split=2, n_estimators=242; total time= 0.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1986; total time= 6.4s [CV] END bootstrap=False, max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1986; total time= 6.4s [CV] END bootstrap=False, max_depth=20, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1986; total time= 6.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=10, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.5s [CV] END bootstrap=False, max_depth=10, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.5s [CV] END bootstrap=False, max_depth=10, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 5.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=110, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, max_depth=110, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, max_depth=110, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=46, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=316; total time= 0.7s [CV] END bootstrap=True, max_depth=46, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=316; total time= 0.7s [CV] END bootstrap=True, max_depth=46, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=316; total time= 0.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=60, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, max_depth=60, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, max_depth=60, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.5s [CV] END bootstrap=False, max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.5s [CV] END bootstrap=False, max_depth=10, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=87, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1978; total time= 4.6s [CV] END bootstrap=True, max_depth=87, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1978; total time= 4.7s [CV] END bootstrap=True, max_depth=87, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1978; total time= 4.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=61, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1920; total time= 6.2s [CV] END bootstrap=False, max_depth=61, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1920; total time= 6.2s [CV] END bootstrap=False, max_depth=61, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1920; total time= 6.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=37, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 4.5s [CV] END bootstrap=True, max_depth=37, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 4.5s [CV] END bootstrap=True, max_depth=37, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 4.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=92, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1981; total time= 5.0s [CV] END bootstrap=True, max_depth=92, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1981; total time= 5.0s [CV] END bootstrap=True, max_depth=92, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1981; total time= 5.1s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=14, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=810; total time= 2.7s [CV] END bootstrap=False, max_depth=14, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=810; total time= 2.8s [CV] END bootstrap=False, max_depth=14, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=810; total time= 2.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=29, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=418; total time= 1.4s [CV] END bootstrap=False, max_depth=29, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=418; total time= 1.4s [CV] END bootstrap=False, max_depth=29, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=418; total time= 1.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=76, max_features=sqrt, min_samples_leaf=3, min_samples_split=2, n_estimators=1934; total time= 5.9s [CV] END bootstrap=False, max_depth=76, max_features=sqrt, min_samples_leaf=3, min_samples_split=2, n_estimators=1934; total time= 5.9s [CV] END bootstrap=False, max_depth=76, max_features=sqrt, min_samples_leaf=3, min_samples_split=2, n_estimators=1934; total time= 5.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=100, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1995; total time= 5.0s [CV] END bootstrap=True, max_depth=100, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1995; total time= 5.0s [CV] END bootstrap=True, max_depth=100, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1995; total time= 5.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=60, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1937; total time= 6.2s [CV] END bootstrap=False, max_depth=60, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1937; total time= 6.2s [CV] END bootstrap=False, max_depth=60, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1937; total time= 6.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=99, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1888; total time= 3.6s [CV] END bootstrap=True, max_depth=99, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1888; total time= 3.6s [CV] END bootstrap=True, max_depth=99, max_features=sqrt, min_samples_leaf=10, min_samples_split=2, n_estimators=1888; total time= 3.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=72, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=282; total time= 0.7s [CV] END bootstrap=True, max_depth=72, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=282; total time= 0.7s [CV] END bootstrap=True, max_depth=72, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=282; total time= 0.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=48, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1884; total time= 6.4s [CV] END bootstrap=False, max_depth=48, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1884; total time= 6.4s [CV] END bootstrap=False, max_depth=48, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1884; total time= 6.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=1994; total time= 4.8s [CV] END bootstrap=True, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=1994; total time= 4.8s [CV] END bootstrap=True, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=1994; total time= 4.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=2000; total time= 6.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=109, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=266; total time= 0.9s [CV] END bootstrap=False, max_depth=109, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=266; total time= 0.9s [CV] END bootstrap=False, max_depth=109, max_features=sqrt, min_samples_leaf=1, min_samples_split=3, n_estimators=266; total time= 0.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=23, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=438; total time= 1.0s [CV] END bootstrap=True, max_depth=23, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=438; total time= 1.0s [CV] END bootstrap=True, max_depth=23, max_features=sqrt, min_samples_leaf=2, min_samples_split=10, n_estimators=438; total time= 1.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=23, max_features=sqrt, min_samples_leaf=5, min_samples_split=10, n_estimators=2000; total time= 5.7s [CV] END bootstrap=False, max_depth=23, max_features=sqrt, min_samples_leaf=5, min_samples_split=10, n_estimators=2000; total time= 5.7s [CV] END bootstrap=False, max_depth=23, max_features=sqrt, min_samples_leaf=5, min_samples_split=10, n_estimators=2000; total time= 5.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=74, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1946; total time= 5.7s [CV] END bootstrap=False, max_depth=74, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1946; total time= 5.8s [CV] END bootstrap=False, max_depth=74, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1946; total time= 5.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=83, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1922; total time= 5.0s [CV] END bootstrap=True, max_depth=83, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1922; total time= 5.0s [CV] END bootstrap=True, max_depth=83, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1922; total time= 5.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=96, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1950; total time= 6.8s [CV] END bootstrap=False, max_depth=96, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1950; total time= 6.8s [CV] END bootstrap=False, max_depth=96, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1950; total time= 6.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=79, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=206; total time= 0.5s [CV] END bootstrap=True, max_depth=79, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=206; total time= 0.5s [CV] END bootstrap=True, max_depth=79, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=206; total time= 0.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=98, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1991; total time= 5.9s [CV] END bootstrap=False, max_depth=98, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1991; total time= 5.9s [CV] END bootstrap=False, max_depth=98, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1991; total time= 5.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=104, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1954; total time= 6.6s [CV] END bootstrap=False, max_depth=104, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1954; total time= 6.6s [CV] END bootstrap=False, max_depth=104, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1954; total time= 6.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1428; total time= 4.9s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1428; total time= 4.9s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1428; total time= 4.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1424; total time= 4.8s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1424; total time= 4.8s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1424; total time= 4.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=93, max_features=log2, min_samples_leaf=5, min_samples_split=10, n_estimators=227; total time= 0.5s [CV] END bootstrap=False, max_depth=93, max_features=log2, min_samples_leaf=5, min_samples_split=10, n_estimators=227; total time= 0.6s [CV] END bootstrap=False, max_depth=93, max_features=log2, min_samples_leaf=5, min_samples_split=10, n_estimators=227; total time= 0.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=40, max_features=log2, min_samples_leaf=3, min_samples_split=10, n_estimators=1929; total time= 4.9s [CV] END bootstrap=False, max_depth=40, max_features=log2, min_samples_leaf=3, min_samples_split=10, n_estimators=1929; total time= 4.9s [CV] END bootstrap=False, max_depth=40, max_features=log2, min_samples_leaf=3, min_samples_split=10, n_estimators=1929; total time= 4.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=822; total time= 2.2s [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=822; total time= 2.2s [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=2, min_samples_split=2, n_estimators=822; total time= 2.3s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1426; total time= 4.6s [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1426; total time= 4.6s [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1426; total time= 4.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1464; total time= 5.0s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1464; total time= 5.0s [CV] END bootstrap=False, max_depth=110, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1464; total time= 5.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1534; total time= 4.9s [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1534; total time= 4.9s [CV] END bootstrap=False, max_depth=10, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1534; total time= 4.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=16, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1180; total time= 3.2s [CV] END bootstrap=False, max_depth=16, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1180; total time= 3.2s [CV] END bootstrap=False, max_depth=16, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1180; total time= 3.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=110, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1539; total time= 5.2s [CV] END bootstrap=False, max_depth=110, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1539; total time= 5.2s [CV] END bootstrap=False, max_depth=110, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1539; total time= 5.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=20, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1160; total time= 3.4s [CV] END bootstrap=False, max_depth=20, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1160; total time= 3.4s [CV] END bootstrap=False, max_depth=20, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1160; total time= 3.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=35, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1379; total time= 3.5s [CV] END bootstrap=True, max_depth=35, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1379; total time= 3.5s [CV] END bootstrap=True, max_depth=35, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1379; total time= 3.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=104, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1987; total time= 5.3s [CV] END bootstrap=False, max_depth=104, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1987; total time= 5.3s [CV] END bootstrap=False, max_depth=104, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1987; total time= 5.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=28, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1983; total time= 6.4s [CV] END bootstrap=False, max_depth=28, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1983; total time= 6.4s [CV] END bootstrap=False, max_depth=28, max_features=auto, min_samples_leaf=2, min_samples_split=2, n_estimators=1983; total time= 6.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=63, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1149; total time= 3.3s [CV] END bootstrap=False, max_depth=63, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1149; total time= 3.3s [CV] END bootstrap=False, max_depth=63, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1149; total time= 3.3s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=102, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1228; total time= 2.7s [CV] END bootstrap=True, max_depth=102, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1228; total time= 2.7s [CV] END bootstrap=True, max_depth=102, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1228; total time= 2.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=14, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1149; total time= 3.6s [CV] END bootstrap=False, max_depth=14, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1149; total time= 3.7s [CV] END bootstrap=False, max_depth=14, max_features=sqrt, min_samples_leaf=2, min_samples_split=2, n_estimators=1149; total time= 3.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=18, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1947; total time= 6.2s [CV] END bootstrap=False, max_depth=18, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1947; total time= 6.2s [CV] END bootstrap=False, max_depth=18, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1947; total time= 6.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=98, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1993; total time= 5.0s [CV] END bootstrap=True, max_depth=98, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1993; total time= 5.0s [CV] END bootstrap=True, max_depth=98, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1993; total time= 5.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=42, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1981; total time= 4.4s [CV] END bootstrap=True, max_depth=42, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1981; total time= 4.4s [CV] END bootstrap=True, max_depth=42, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1981; total time= 4.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=30, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=221; total time= 0.6s [CV] END bootstrap=False, max_depth=30, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=221; total time= 0.6s [CV] END bootstrap=False, max_depth=30, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=221; total time= 0.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=109, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=311; total time= 1.1s [CV] END bootstrap=False, max_depth=109, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=311; total time= 1.1s [CV] END bootstrap=False, max_depth=109, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=311; total time= 1.1s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=100, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=262; total time= 0.8s [CV] END bootstrap=False, max_depth=100, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=262; total time= 0.8s [CV] END bootstrap=False, max_depth=100, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=262; total time= 0.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=1, min_samples_split=7, n_estimators=1995; total time= 5.5s [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=1, min_samples_split=7, n_estimators=1995; total time= 5.5s [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=1, min_samples_split=7, n_estimators=1995; total time= 5.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=28, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1340; total time= 2.2s [CV] END bootstrap=True, max_depth=28, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1340; total time= 2.2s [CV] END bootstrap=True, max_depth=28, max_features=log2, min_samples_leaf=10, min_samples_split=10, n_estimators=1340; total time= 2.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=55, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1943; total time= 5.6s [CV] END bootstrap=False, max_depth=55, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1943; total time= 5.6s [CV] END bootstrap=False, max_depth=55, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1943; total time= 5.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=84, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1966; total time= 4.0s [CV] END bootstrap=True, max_depth=84, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1966; total time= 4.0s [CV] END bootstrap=True, max_depth=84, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1966; total time= 4.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=13, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1860; total time= 6.3s [CV] END bootstrap=False, max_depth=13, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1860; total time= 6.3s [CV] END bootstrap=False, max_depth=13, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1860; total time= 6.3s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=95, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1859; total time= 5.4s [CV] END bootstrap=False, max_depth=95, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1859; total time= 5.4s [CV] END bootstrap=False, max_depth=95, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1859; total time= 5.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=32, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1972; total time= 6.6s [CV] END bootstrap=False, max_depth=32, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1972; total time= 6.6s [CV] END bootstrap=False, max_depth=32, max_features=sqrt, min_samples_leaf=1, min_samples_split=2, n_estimators=1972; total time= 6.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=78, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=326; total time= 0.9s [CV] END bootstrap=False, max_depth=78, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=326; total time= 0.9s [CV] END bootstrap=False, max_depth=78, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=326; total time= 0.9s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=11, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=401; total time= 1.1s [CV] END bootstrap=False, max_depth=11, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=401; total time= 1.1s [CV] END bootstrap=False, max_depth=11, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=401; total time= 1.1s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=13, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=290; total time= 1.0s [CV] END bootstrap=False, max_depth=13, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=290; total time= 1.0s [CV] END bootstrap=False, max_depth=13, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=290; total time= 1.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=21, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=227; total time= 0.7s [CV] END bootstrap=False, max_depth=21, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=227; total time= 0.7s [CV] END bootstrap=False, max_depth=21, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=227; total time= 0.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=92, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1752; total time= 3.7s [CV] END bootstrap=False, max_depth=92, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1752; total time= 3.7s [CV] END bootstrap=False, max_depth=92, max_features=log2, min_samples_leaf=10, min_samples_split=2, n_estimators=1752; total time= 3.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=102, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=291; total time= 0.8s [CV] END bootstrap=False, max_depth=102, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=291; total time= 0.8s [CV] END bootstrap=False, max_depth=102, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=291; total time= 0.8s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=103, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1926; total time= 5.6s [CV] END bootstrap=False, max_depth=103, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1926; total time= 5.6s [CV] END bootstrap=False, max_depth=103, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1926; total time= 5.6s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=12, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1984; total time= 4.9s [CV] END bootstrap=True, max_depth=12, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1984; total time= 5.0s [CV] END bootstrap=True, max_depth=12, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=1984; total time= 5.0s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=86, max_features=log2, min_samples_leaf=1, min_samples_split=9, n_estimators=327; total time= 0.7s [CV] END bootstrap=True, max_depth=86, max_features=log2, min_samples_leaf=1, min_samples_split=9, n_estimators=327; total time= 0.7s [CV] END bootstrap=True, max_depth=86, max_features=log2, min_samples_leaf=1, min_samples_split=9, n_estimators=327; total time= 0.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=44, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1949; total time= 3.7s [CV] END bootstrap=True, max_depth=44, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1949; total time= 3.7s [CV] END bootstrap=True, max_depth=44, max_features=log2, min_samples_leaf=4, min_samples_split=2, n_estimators=1949; total time= 3.7s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=32, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1945; total time= 4.5s [CV] END bootstrap=True, max_depth=32, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1945; total time= 4.5s [CV] END bootstrap=True, max_depth=32, max_features=sqrt, min_samples_leaf=1, min_samples_split=10, n_estimators=1945; total time= 4.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=109, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=210; total time= 0.5s [CV] END bootstrap=True, max_depth=109, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=210; total time= 0.5s [CV] END bootstrap=True, max_depth=109, max_features=auto, min_samples_leaf=1, min_samples_split=2, n_estimators=210; total time= 0.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=True, max_depth=91, max_features=auto, min_samples_leaf=5, min_samples_split=10, n_estimators=1922; total time= 4.0s [CV] END bootstrap=True, max_depth=91, max_features=auto, min_samples_leaf=5, min_samples_split=10, n_estimators=1922; total time= 4.0s [CV] END bootstrap=True, max_depth=91, max_features=auto, min_samples_leaf=5, min_samples_split=10, n_estimators=1922; total time= 4.1s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=81, max_features=log2, min_samples_leaf=7, min_samples_split=2, n_estimators=267; total time= 0.5s [CV] END bootstrap=True, max_depth=81, max_features=log2, min_samples_leaf=7, min_samples_split=2, n_estimators=267; total time= 0.5s [CV] END bootstrap=True, max_depth=81, max_features=log2, min_samples_leaf=7, min_samples_split=2, n_estimators=267; total time= 0.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=True, max_depth=50, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1986; total time= 4.4s [CV] END bootstrap=True, max_depth=50, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1986; total time= 4.4s [CV] END bootstrap=True, max_depth=50, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1986; total time= 4.4s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=458; total time= 1.3s [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=458; total time= 1.3s [CV] END bootstrap=False, max_depth=108, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=458; total time= 1.3s Fitting 3 folds for each of 1 candidates, totalling 3 fits
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn( /Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/ensemble/_forest.py:424: FutureWarning: `max_features='auto'` has been deprecated in 1.1 and will be removed in 1.3. To keep the past behaviour, explicitly set `max_features='sqrt'` or remove this parameter as it is also the default value for RandomForestClassifiers and ExtraTreesClassifiers. warn(
[CV] END bootstrap=False, max_depth=109, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1937; total time= 6.1s [CV] END bootstrap=False, max_depth=109, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1937; total time= 6.1s [CV] END bootstrap=False, max_depth=109, max_features=auto, min_samples_leaf=1, min_samples_split=10, n_estimators=1937; total time= 6.2s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=100, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1897; total time= 5.5s [CV] END bootstrap=False, max_depth=100, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1897; total time= 5.5s [CV] END bootstrap=False, max_depth=100, max_features=log2, min_samples_leaf=1, min_samples_split=2, n_estimators=1897; total time= 5.5s Fitting 3 folds for each of 1 candidates, totalling 3 fits [CV] END bootstrap=False, max_depth=109, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1954; total time= 5.2s [CV] END bootstrap=False, max_depth=109, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1954; total time= 5.2s [CV] END bootstrap=False, max_depth=109, max_features=log2, min_samples_leaf=1, min_samples_split=10, n_estimators=1954; total time= 5.3s
BayesSearchCV(cv=3, estimator=RandomForestClassifier(random_state=42),
n_iter=100, n_jobs=-1, random_state=42,
search_spaces={'bootstrap': Categorical(categories=(True, False), prior=None),
'max_depth': Integer(low=10, high=110, prior='uniform', transform='normalize'),
'max_features': Categorical(categories=('auto', 'sqrt', 'log2'), prior=None),
'min_samples_leaf': Integer(low=1, high=10, prior='uniform', transform='normalize'),
'min_samples_split': Integer(low=2, high=10, prior='uniform', transform='normalize'),
'n_estimators': Integer(low=200, high=2000, prior='uniform', transform='normalize')},
verbose=2)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
BayesSearchCV(cv=3, estimator=RandomForestClassifier(random_state=42),
n_iter=100, n_jobs=-1, random_state=42,
search_spaces={'bootstrap': Categorical(categories=(True, False), prior=None),
'max_depth': Integer(low=10, high=110, prior='uniform', transform='normalize'),
'max_features': Categorical(categories=('auto', 'sqrt', 'log2'), prior=None),
'min_samples_leaf': Integer(low=1, high=10, prior='uniform', transform='normalize'),
'min_samples_split': Integer(low=2, high=10, prior='uniform', transform='normalize'),
'n_estimators': Integer(low=200, high=2000, prior='uniform', transform='normalize')},
verbose=2)RandomForestClassifier(random_state=42)
RandomForestClassifier(random_state=42)
# Best parameters and accuracy
print(f"Best parameters: {bayes_search.best_params_}")
print(f"Best cross-validation accuracy: {bayes_search.best_score_}")
Best parameters: OrderedDict([('bootstrap', False), ('max_depth', 78), ('max_features', 'log2'), ('min_samples_leaf', 1), ('min_samples_split', 2), ('n_estimators', 326)])
Best cross-validation accuracy: 0.6839424046489179
# Evaluate on the test set
best_rf_bayes = bayes_search.best_estimator_
#test_accuracy_bayes = best_rf_bayes.score(X_test, y_test)
#print(f"Test accuracy: {test_accuracy_bayes:.4f}")
best_rf_bayes
RandomForestClassifier(bootstrap=False, max_depth=78, max_features='log2',
n_estimators=326, random_state=42)In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomForestClassifier(bootstrap=False, max_depth=78, max_features='log2',
n_estimators=326, random_state=42)y_pred_bayes = best_rf_bayes.predict(X_test)
accuracy_score(y_pred_bayes, y_test)
0.7321428571428571
So the accuracy of our random forest with Bayesian search is better then the others: 73%. I also used less interactions (just 100 and not 500 as in the random search). So from the simplest random forest (the one without any cross validation or any search) with accuracy 66% we reached 73%. It is not very high but considering that I have 5 classes to predict, it is pretty good.
Again I am going to plot the confusion matrix in order to see how the predictions both the right and the wrong ones have been distributed.
cf_matrix_rf_bayes = confusion_matrix(y_test, y_pred_bayes)
cf_matrix_rf_bayes
array([[51, 5, 3, 2, 4],
[ 2, 39, 2, 7, 2],
[ 6, 1, 42, 1, 5],
[ 8, 6, 0, 38, 4],
[ 4, 5, 7, 1, 35]])
plt.imshow(cf_matrix_rf_bayes, interpolation='nearest', cmap='Blues')
plt.title('Confusion Matrix for Random Forest with Bayes Search')
plt.colorbar()
# Draw the grid boxes
class_names = ['0', '1', '2', '3', '4']
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# Draw the text boxes
thresh = cf_matrix_rf_bayes.max() / 2.
for i, j in itertools.product(range(cf_matrix_rf_bayes.shape[0]), range(cf_matrix_rf_bayes.shape[1])):
plt.text(j, i, cf_matrix_rf_bayes[i, j],
horizontalalignment="center",
color="white" if cf_matrix_rf_bayes[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
From the confusion matrix it is possible to notice that the random forest predicted wrong 20 data points as class 0, 17 as class 1, 12 as class 2, 11 as class 3 and 15 data points as class 4. So the most probablematic is always false 0. (also in the one others).
To see the size of the random forest I plot one of the tree.
from sklearn.tree import plot_tree
fig = plt.figure(figsize=(8,8))
plt.figure(figsize=(80,40))
plot_tree(best_rf_bayes.estimators_[0], feature_names=df_data_points.columns, class_names=['0', '1', '2', '3', '4'], filled=True)
fig.savefig('rf_individualtree.png')
<Figure size 800x800 with 0 Axes>
Finally since I have implemented a random forest, I want to see if there are some features that are more important then the others. Therefore I make a rank in order to understand the impact of each of the 25 features (again I am applying this just to the last random forest, the one performed with the Bayes Search)
df_importance = pd.DataFrame(best_rf_bayes.feature_importances_, index=df_data_points.columns, columns=['importance'])
df_importance_sorted = df_importance.sort_values(by='importance', ascending=False)
df_importance_sorted
| importance | |
|---|---|
| feature_20 | 0.062109 |
| feature_19 | 0.057101 |
| feature_11 | 0.055179 |
| feature_9 | 0.053888 |
| feature_3 | 0.052883 |
| feature_7 | 0.051550 |
| feature_17 | 0.047547 |
| feature_6 | 0.044916 |
| feature_12 | 0.044347 |
| feature_25 | 0.043836 |
| feature_24 | 0.042901 |
| feature_16 | 0.042853 |
| feature_2 | 0.041756 |
| feature_8 | 0.041355 |
| feature_1 | 0.040886 |
| feature_14 | 0.040595 |
| feature_5 | 0.038976 |
| feature_23 | 0.038294 |
| feature_4 | 0.023685 |
| feature_15 | 0.023309 |
| feature_10 | 0.023308 |
| feature_18 | 0.022646 |
| feature_13 | 0.022306 |
| feature_21 | 0.022169 |
| feature_22 | 0.021603 |
What it is immediately clear is that the features do not have a very great difference on their impact on the data points (infact feature 20, the first one, has importance of 0.062 while the last one has an importance of 0.021). This is probably to the fact that this data is generated from a normal distribution.
Moreover this could be also a cause to not manage to get an higher accuracy.
¶
4.1.5 RANDOM FOREST MODEL SELECTION
In this section, I am going to evaluate the performance of the Random Forest models using different hyperparameter search methods: Grid Search, Random Search, and Bayesian Search.
I consider three key metrics (in addition to accuracy and confusion matrix already computed for each single method in the above steps):
- precision score that is the ratio between True positive and the sum of True Positive and False Positives (TP/(TP+FP));
- recall (also called sensitivity) that is the ratio between True Positives and the sum of True Positive and False Negative (TP/(TP+FN))
- f1-score that is the weighted average of the precision and recall score.
Moreover, since I had multiple classes as a labels (and not a binary situation) I used the average method 'macro' which gives the same importance to each class (this choice comes from the fact that the classes are well balanced and therefore was useless to give more importance to some specific class).
Finally, I generate classification reports for each search method to provide a detailed breakdown of the model's performance for each class.
average_method ='macro'
for score in (precision_score, recall_score, f1_score):
sgrid_stat_rf = score(y_test, y_pred_grid, average=average_method)
srandom_stat_rf = score(y_test, y_pred_g_random, average=average_method)
sbayes_stat_rf = score(y_test, y_pred_bayes, average=average_method)
print(score.__name__, (sgrid_stat_rf, srandom_stat_rf, sbayes_stat_rf))
precision_score (0.7189090909090909, 0.7289155811508753, 0.7336052824885823) recall_score (0.712017982017982, 0.7256543456543457, 0.72998001998002) f1_score (0.7135688524608459, 0.7262796461786843, 0.730589691534106)
c_report_grid_rf = classification_report(y_test, y_pred_grid, target_names=['0', '1', '2', '3', '4'])
c_report_random_rf = classification_report(y_test, y_pred_g_random, target_names=['0', '1', '2', '3', '4'])
c_report_bayes_rf = classification_report(y_test, y_pred_bayes, target_names=['0', '1', '2', '3', '4'])
print(c_report_grid_rf, c_report_random_rf, c_report_bayes_rf)
precision recall f1-score support
0 0.67 0.77 0.71 65
1 0.73 0.77 0.75 52
2 0.74 0.67 0.70 55
3 0.73 0.71 0.72 56
4 0.73 0.63 0.68 52
accuracy 0.71 280
macro avg 0.72 0.71 0.71 280
weighted avg 0.72 0.71 0.71 280
precision recall f1-score support
0 0.72 0.80 0.76 65
1 0.73 0.77 0.75 52
2 0.73 0.69 0.71 55
3 0.78 0.71 0.75 56
4 0.68 0.65 0.67 52
accuracy 0.73 280
macro avg 0.73 0.73 0.73 280
weighted avg 0.73 0.73 0.73 280
precision recall f1-score support
0 0.72 0.78 0.75 65
1 0.70 0.75 0.72 52
2 0.78 0.76 0.77 55
3 0.78 0.68 0.72 56
4 0.70 0.67 0.69 52
accuracy 0.73 280
macro avg 0.73 0.73 0.73 280
weighted avg 0.73 0.73 0.73 280
As it is possible to notice the best Random forest model is the one got with Bayes Search which reaches almost 73% in each metric I considered. This will be the Random Forest I will compare with the best KNN model (see the steps below).
So summarizing the best random forest model found with Bayesian search has the following hyperparameters:
- Bootstrap = False
- Max_depth = 78
- Max_features = log2
- Min_samples_leaf = 1
- Min_samples_split = 2
- N_estimators = 326
¶
4.2 KNN
I start now implementing the K-Nearest Neighbors, again starting implementing it in the simplest way (no cross validation, no search) and then adding hyperparameters tuning techniques to see if the accuracy improves
¶
4.2.1 SIMPLE KNN
I start just implementing a KNN model without any hyperparameter tuning technique, fitting it and make it predict the test data.
The accuracy is again not very high (67.85%, so a little bit higher then the accuracy of the first random forest implemented).
knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
KNeighborsClassifier()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
KNeighborsClassifier()
y_pred_knn = knn.predict(X_test)
accuracy_score(y_pred_knn, y_test)
0.6785714285714286
Now since it is known that the number of neighbours is pivotal in the model performance (and before I used the default value, since I did not specify it), I am going to make several manual trials of how the model varies with changing in the neighbors value. (starting without any kind of cross validation).
accuracy = []
k_values = list(range(1, 100, 2))
for k in k_values:
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
accuracy.append(accuracy_score(y_pred, y_test))
# Find the k value with maximum accuracy
max_accuracy_index = np.argmax(accuracy)
k_max_accuracy = k_values[max_accuracy_index]
print(f"The number of neighbors where the accuracy is maximized is: {k_max_accuracy}")
# First plot
plt.figure(figsize=(10, 6)) # Adjust size as needed
plt.subplot(2, 1, 1) # 2 rows, 1 column, first plot
plt.xlabel('Number of Neighbours')
plt.ylabel('Accuracy')
plt.plot(range(1, 100, 2), accuracy, color='blue', linestyle='dashed', marker='o', markerfacecolor='red', markersize=10)
# Second plot
plt.subplot(2, 1, 2) # 2 rows, 1 column, second plot
plt.bar([i for i in range(1, len(accuracy)*2, 2)], accuracy) # Adjust range to match length of accuracy
plt.xlabel('Number of Neighbours')
plt.ylabel('Accuracy')
plt.tight_layout() # Adjusts subplot params so that subplots are nicely fit in the figure.
plt.show()
The number of neighbors where the accuracy is maximized is: 9
From this simple experiment of testing KNN with different neighbours values it is possible to notice that the highest accuracy is reached between 0 and 20 (in particular at 9 with accuracy of almost 72% which is higher then the 68% found at the default k=5 tried at the beginning), while after 20 (a part for a small peak) the accuracy decreases drastically until to arrive at approximately 60% with k=99. Moreover in this situation I have used a default metric and default weights (in grid search, random search and bayes search I will try to look for the best combinations).
Below an experiment with using 5 cross validations and what I get is a worst or in some situation similar result.
accuracy = []
k_values = list(range(1, 100, 2))
for k in k_values:
knn = KNeighborsClassifier(n_neighbors=k)
scores = cross_val_score(knn, df_data_points, df_labels, cv=5, scoring='accuracy')
accuracy.append(scores.mean())
# Find the k value with maximum accuracy
max_accuracy_index = np.argmax(accuracy)
k_max_accuracy = k_values[max_accuracy_index]
print(f"The number of neighbors where the accuracy is maximized is: {k_max_accuracy}")
# First plot
plt.figure(figsize=(10, 6)) # Adjust size as needed
plt.subplot(2, 1, 1) # 2 rows, 1 column, first plot
plt.xlabel('Number of Neighbours')
plt.ylabel('Accuracy')
plt.plot(range(1, 100, 2), accuracy, color='blue', linestyle='dashed', marker='o', markerfacecolor='red', markersize=10)
# Second plot
plt.subplot(2, 1, 2) # 2 rows, 1 column, second plot
plt.bar([i for i in range(1, len(accuracy)*2, 2)], accuracy) # Adjust range to match length of accuracy
plt.xlabel('Number of Neighbours')
plt.ylabel('Accuracy')
plt.tight_layout() # Adjusts subplot params so that subplots are nicely fit in the figure.
plt.show()
The number of neighbors where the accuracy is maximized is: 9
¶
4.2.2 KNN WITH GRID SEARCH
Now I have decided to use a KNN classifier with a Grid Search to find the best hyperparameters. I consider as hyperparameters that have a huge impact on our KNN the weights, the metric (that measures the distance between data points), the algorithm and indeed the number of neighbors (already found before) used.
Since it is impractical to explore all possible combinations due to time and computational constraints, I have selected a subset of hyperparameters for the grid search.
In particular:
- for the number of neighbours I chose the interval of values 1-20 thanks to the results discovered in the former point;
- for the weights which determine how each neighbor contributes to the classification decision I chose uniform (all neighbors contribute equally to the classification decision) and distance (closer neighbors contribute more to the classification decision than farther ones).
- for the metric I chose the most famous euclidean, manhattan, minkowski, and chebyshev.
- for the algorithm which tells us the most efficient way to compute the neighbors I chose auto, ball tree and kd_tree.
Finally for the grid configuration I used 5-fold cross-validation (as I did with RF grid search).
# Define the parameter grid
param_grid_k = {
'n_neighbors': list(range(1, 20, 2)),
'weights': ['uniform', 'distance'],
'metric': ['euclidean', 'manhattan', 'minkowski', 'chebyshev'],
'algorithm': ['auto', 'ball_tree', 'kd_tree']
}
# Initialize the KNN classifier
knn_g = KNeighborsClassifier()
# Initialize GridSearchCV
grid_search_knn = GridSearchCV(estimator=knn_g, param_grid=param_grid_k, cv=5, n_jobs=-1, verbose=2, scoring='accuracy')
# Fit GridSearchCV
grid_search_knn.fit(X_train, y_train)
# Best parameters and accuracy
print(f"Best parameters: {grid_search_knn.best_params_}")
print(f"Best cross-validation accuracy: {grid_search_knn.best_score_}")
Fitting 5 folds for each of 240 candidates, totalling 1200 fits
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.1s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.1s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
Best parameters: {'algorithm': 'auto', 'metric': 'manhattan', 'n_neighbors': 9, 'weights': 'distance'}
Best cross-validation accuracy: 0.6776785714285716
best_knn_grid = grid_search_knn.best_estimator_
best_knn_grid
KNeighborsClassifier(metric='manhattan', n_neighbors=9, weights='distance')In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
KNeighborsClassifier(metric='manhattan', n_neighbors=9, weights='distance')
# Evaluate on the test set with the best estimator
y_pred_best_k_grid = best_knn_grid.predict(X_test)
best_accuracy = accuracy_score(y_test, y_pred_best_k_grid)
print(f'Best KNN Test Accuracy: {best_accuracy:.4f}')
Best KNN Test Accuracy: 0.7071
As it was possible to imagine, I get as test accuracy 70.71% with n_neighbours = 9 (I already saw this in the former step), the weight is distance and as metric the manhattan distance. This improves the initial accuracy of the first KNN model I tested (in that case it was approximately 67%).
I now represent graphically the confusion matrix which gives in details the distribution of the prediction (in the sense that it is possible to see how many right prediction the model gets for each class and also the wrong prediction for each class and what class was instead chosen). So it is very useful to have a precise idea on how the predictions happened.
cf_matrix_knn_grid = confusion_matrix(y_test, y_pred_best_k_grid)
cf_matrix_knn_grid
array([[50, 4, 3, 3, 5],
[ 1, 43, 1, 3, 4],
[10, 1, 36, 2, 6],
[ 9, 10, 0, 34, 3],
[ 4, 2, 8, 3, 35]])
#plt.figure(figsize=(10, 7))
plt.imshow(cf_matrix_knn_grid, interpolation='nearest', cmap='Blues')
plt.title('Confusion Matrix for KNN with Grid Search')
plt.colorbar()
# Draw the grid boxes
class_names = ['0', '1', '2', '3', '4']
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# Draw the text boxes
thresh = cf_matrix_knn_grid.max() / 2.
for i, j in itertools.product(range(cf_matrix_knn_grid.shape[0]), range(cf_matrix_knn_grid.shape[1])):
plt.text(j, i, cf_matrix_knn_grid[i, j],
horizontalalignment="center",
color="white" if cf_matrix_knn_grid[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
From the confusion matrix it is possible to notice that the KNN with grid search predicted wrong 24 data points as class 0, 17 as class 1, 12 as class 2, 11 as class 3 and 18 data points as class 4. So the most probablematic were false 0 and false 4. But this makes sense also because class 0 and class 4 were the most represented classes in the dataset (it is important to notice that this is a very small difference but it was nice to be pointed out).
I now try to implement a KNN with a random search to see if something changes.
¶
4.2.3 KNN WITH RANDOM SEARCH
Now I have decided to use a KNN classifier with a Random Search to find the best hyperparameters. As before I consider as hyperparameters the weights, the metric, the algorithm and the number of neighbors.
I also kept the same values/intervals for the hyperparameters of the grid search, in particular:
- for the number of neighbours I chose the interval of values 1-20 thanks to the results discovered in the first section of KNN;
- for the weights I chose uniform and distance.
- for the metric I chose again the most famous euclidean, manhattan, minkowski, and chebyshev.
- for the algorithm I chose auto, ball tree and kd_tree.
Finally for the random configuration I used 5-fold cross-validation and 500 number of iterations.
param_dist_random = {
'n_neighbors': list(range(1, 20, 2)),
'weights': ['uniform', 'distance'],
'metric': ['euclidean', 'manhattan', 'minkowski', 'chebyshev'],
'algorithm': ['auto', 'ball_tree', 'kd_tree']
}
knn_random = KNeighborsClassifier()
# Initialize RandomizedSearchCV
random_search_knn = RandomizedSearchCV(estimator=knn_random, param_distributions=param_dist_random, n_iter=500, cv=5, n_jobs=-1, verbose=2, scoring='accuracy', random_state=42)
# Fit RandomizedSearchCV
random_search_knn.fit(X_train, y_train)
# Best parameters and accuracy
print(f"Best parameters: {random_search_knn.best_params_}")
print(f"Best cross-validation accuracy: {random_search_knn.best_score_}")
Fitting 5 folds for each of 240 candidates, totalling 1200 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/sklearn/model_selection/_search.py:305: UserWarning: The total space of parameters 240 is smaller than n_iter=500. Running 240 iterations. For exhaustive searches, use GridSearchCV. warnings.warn(
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s[CV] END algorithm=auto, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=auto, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=3, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=9, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=11, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=15, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=17, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=19, weights=distance; total time= 0.0s
Best parameters: {'weights': 'distance', 'n_neighbors': 9, 'metric': 'manhattan', 'algorithm': 'auto'}
Best cross-validation accuracy: 0.6776785714285716
best_knn_random = random_search_knn.best_estimator_
best_knn_random
KNeighborsClassifier(metric='manhattan', n_neighbors=9, weights='distance')In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
KNeighborsClassifier(metric='manhattan', n_neighbors=9, weights='distance')
# Evaluate on the test set with the best estimator
y_pred_best_random_knn = best_knn_random.predict(X_test)
best_accuracy_random_knn = accuracy_score(y_test, y_pred_best_random_knn)
print(f'Best KNN Test Accuracy (Random Search): {best_accuracy_random_knn:.4f}')
Best KNN Test Accuracy (Random Search): 0.7071
Also with random search and same parameters as in the grid search I get the same result (differently instead from the random forest scenario where in the random search I modified some parameters).
I now represent graphically the confusion matrix which gives in details the distribution of the prediction (in the sense that it is possible to see how many right prediction the model gets for each class and also the wrong prediction for each class and what class was instead chosen). So it is very useful to have a precise idea on how the predictions happened.
cf_matrix_knn_random = confusion_matrix(y_test, y_pred_best_random_knn)
cf_matrix_knn_random
array([[50, 4, 3, 3, 5],
[ 1, 43, 1, 3, 4],
[10, 1, 36, 2, 6],
[ 9, 10, 0, 34, 3],
[ 4, 2, 8, 3, 35]])
#plt.figure(figsize=(10, 7))
plt.imshow(cf_matrix_knn_random, interpolation='nearest', cmap='Blues')
plt.title('Confusion Matrix for KNN with Random Search')
plt.colorbar()
# Draw the grid boxes
class_names = ['0', '1', '2', '3', '4']
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# Draw the text boxes
thresh = cf_matrix_knn_random.max() / 2.
for i, j in itertools.product(range(cf_matrix_knn_random.shape[0]), range(cf_matrix_knn_random.shape[1])):
plt.text(j, i, cf_matrix_knn_random[i, j],
horizontalalignment="center",
color="white" if cf_matrix_knn_random[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
From the confusion matrix it is possible to notice that the KNN with random search predicted wrong 24 data points as class 0, 17 as class 1, 12 as class 2, 11 as class 3 and 18 data points as class 4. So the most probablematic were false 0 and false 4. But this makes sense also because class 0 and class 4 were the most represented classes in the dataset (it is important to notice that this is a very small difference but it was nice to be pointed out).
I now try to implement a KNN with a bayesian search to see if something changes.
¶
4.2.4 KNN WITH BAYESIAN SEARCH
Now I have decided to use a KNN classifier with a Bayesian Search to find the best hyperparameters. As before I consider as hyperparameters the weights, the metric, the algorithm and the number of neighbors.
I also kept the same values/intervals for the hyperparameters search space of the random search, in particular:
- for the number of neighbours I chose the interval of values 1-20 thanks to the results discovered in the first section of KNN;
- for the weights I chose uniform and distance.
- for the metric I chose again the most famous euclidean, manhattan, minkowski, and chebyshev.
- for the algorithm I chose auto, ball tree and kd_tree.
Finally for the bayesian configuration I used 5-fold cross-validation and 100 number of iterations (so I decreased the number of iterations compared to the random search).
search_space_k = {
'n_neighbors': Integer(1, 20),
'weights': Categorical(['uniform', 'distance']),
'metric': Categorical(['euclidean', 'manhattan', 'minkowski', 'chebyshev']),
'algorithm': Categorical(['auto', 'ball_tree', 'kd_tree'])
}
# Initialize the KNN classifier
knn_b = KNeighborsClassifier()
# Initialize BayesSearchCV
bayes_search = BayesSearchCV(
estimator=knn_b,
search_spaces=search_space_k,
n_iter=100, # Number of iterations
cv=5, # Number of cross-validation folds
n_jobs=-1,
verbose=2,
random_state=42,
scoring='accuracy'
)
# Fit BayesSearchCV
bayes_search.fit(X_train, y_train)
# Best parameters and accuracy
print(f"Best parameters: {bayes_search.best_params_}")
print(f"Best cross-validation accuracy: {bayes_search.best_score_}")
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=19, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=7, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=3, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=4, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=8, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=10, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=18, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=15, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=1, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=1, weights=distance; total time= 0.0s
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=13, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=6, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=17, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=14, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=1, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=12, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s[CV] END algorithm=auto, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=14, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=11, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=9, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=6, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=1, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=20, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=8, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=10, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=18, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=18, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=18, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=15, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=3, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=4, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=14, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=14, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=14, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=14, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=14, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=12, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=14, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=14, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=10, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=10, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=16, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=9, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=7, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=3, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=16, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=17, weights=uniform; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['kd_tree', 'manhattan', 12, 'distance'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=4, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=4, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=4, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=12, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=19, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=1, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=5, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=7, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=17, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=10, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=18, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=18, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=euclidean, n_neighbors=15, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=17, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=chebyshev, n_neighbors=9, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=20, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=5, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=11, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=uniform; total time= 0.0s [CV] END algorithm=kd_tree, metric=manhattan, n_neighbors=12, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=13, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=8, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=8, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=8, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=8, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=8, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=3, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=6, weights=uniform; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['auto', 'minkowski', 10, 'uniform'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=10, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=10, weights=uniform; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['ball_tree', 'euclidean', 2, 'distance'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=2, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=2, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=2, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=2, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=euclidean, n_neighbors=2, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=16, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=16, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=16, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=16, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=16, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=manhattan, n_neighbors=19, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=minkowski, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=6, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=minkowski, n_neighbors=6, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=4, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=minkowski, n_neighbors=4, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=5, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=6, weights=uniform; total time= 0.0s [CV] END algorithm=ball_tree, metric=chebyshev, n_neighbors=6, weights=uniform; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=13, weights=uniform; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['kd_tree', 'minkowski', 13, 'distance'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=minkowski, n_neighbors=13, weights=distance; total time= 0.0s Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=16, weights=distance; total time= 0.0s [CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=16, weights=distance; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['auto', 'manhattan', 3, 'uniform'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s [CV] END algorithm=auto, metric=manhattan, n_neighbors=3, weights=uniform; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['auto', 'euclidean', 8, 'distance'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits [CV] END algorithm=auto, metric=euclidean, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=8, weights=distance; total time= 0.0s [CV] END algorithm=auto, metric=euclidean, n_neighbors=8, weights=distance; total time= 0.0s
/Users/federicopezzoli/opt/anaconda3/lib/python3.9/site-packages/skopt/optimizer/optimizer.py:517: UserWarning: The objective has been evaluated at point ['ball_tree', 'manhattan', 9, 'distance'] before, using random point ['kd_tree', 'chebyshev', 13, 'uniform'] warnings.warn(
Fitting 5 folds for each of 1 candidates, totalling 5 fits
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
[CV] END algorithm=kd_tree, metric=chebyshev, n_neighbors=13, weights=uniform; total time= 0.0s
Best parameters: OrderedDict([('algorithm', 'auto'), ('metric', 'manhattan'), ('n_neighbors', 9), ('weights', 'distance')])
Best cross-validation accuracy: 0.6776785714285716
best_knn_bayes = bayes_search.best_estimator_
best_knn_bayes
KNeighborsClassifier(metric='manhattan', n_neighbors=9, weights='distance')In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
KNeighborsClassifier(metric='manhattan', n_neighbors=9, weights='distance')
y_pred_best_bayes_knn = best_knn_bayes.predict(X_test)
best_accuracy_bayes_knn = accuracy_score(y_test, y_pred_best_bayes_knn)
print(f'Best KNN Test Accuracy (Bayesian Search): {best_accuracy_bayes_knn:.4f}')
Best KNN Test Accuracy (Bayesian Search): 0.7071
Also with bayesian search and similar parameters as in the random search I get the same accuracy (differently instead from the random forest scenario where in the bayesian search I got different accuracy).
I now represent graphically the confusion matrix which gives in details the distribution of the prediction (in the sense that it is possible to see how many right prediction the model gets for each class and also the wrong prediction for each class and what class was instead chosen). So it is very useful to have a precise idea on how the predictions happened.
cf_matrix_knn_bayes = confusion_matrix(y_test, y_pred_best_bayes_knn)
cf_matrix_knn_bayes
array([[50, 4, 3, 3, 5],
[ 1, 43, 1, 3, 4],
[10, 1, 36, 2, 6],
[ 9, 10, 0, 34, 3],
[ 4, 2, 8, 3, 35]])
#plt.figure(figsize=(10, 7))
plt.imshow(cf_matrix_knn_bayes, interpolation='nearest', cmap='Blues')
plt.title('Confusion Matrix for KNN with Bayes Search')
plt.colorbar()
# Draw the grid boxes
class_names = ['0', '1', '2', '3', '4']
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# Draw the text boxes
thresh = cf_matrix_knn_bayes.max() / 2.
for i, j in itertools.product(range(cf_matrix_knn_bayes.shape[0]), range(cf_matrix_knn_bayes.shape[1])):
plt.text(j, i, cf_matrix_knn_bayes[i, j],
horizontalalignment="center",
color="white" if cf_matrix_knn_bayes[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()
From the confusion matrix it is possible to notice that the KNN with grid search predicted wrong 24 data points as class 0, 17 as class 1, 12 as class 2, 11 as class 3 and 18 data points as class 4. So the most probablematic were false 0 and false 4. But this makes sense also because class 0 and class 4 were the most represented classes in the dataset (it is important to notice that this is a very small difference but it was nice to be pointed out).
¶
4.2.5 KNN MODEL SELECTION
In this section, I am going to evaluate the performance of the KNN models using different hyperparameter search methods: Grid Search, Random Search, and Bayesian Search.
I consider three key metrics (in addition to accuracy and confusion matrix already computed for each single method in the above steps):
- precision score that is the ratio between True positive and the sum of True Positive and False Positives (TP/(TP+FP));
- recall (also called sensitivity) that is the ratio between True Positives and the sum of True Positive and False Negative (TP/(TP+FN))
- f1-score that is the weighted average of the precision and recall score.
Moreover, since I had multiple classes as a labels (and not a binary situation) I used the average method 'macro' which gives the same importance to each class (this choice comes from the fact that the classes are well balanced and therefore was useless to give more importance to some specific class).
Finally, I generate classification reports for each search method to provide a detailed breakdown of the model's performance for each class.
average_method ='macro'
for score in (precision_score, recall_score, f1_score):
sgrid_stat_knn = score(y_test, y_pred_best_k_grid, average=average_method)
srandom_stat_knn = score(y_test, y_pred_best_random_knn, average=average_method)
sbayes_stat_knn = score(y_test, y_pred_best_bayes_knn, average=average_method)
print(score.__name__, (sgrid_stat_knn, srandom_stat_knn, sbayes_stat_knn))
precision_score (0.7116550512776928, 0.7116550512776928, 0.7116550512776928) recall_score (0.7061838161838162, 0.7061838161838162, 0.7061838161838162) f1_score (0.7052489445803459, 0.7052489445803459, 0.7052489445803459)
c_report_grid_knn = classification_report(y_test, y_pred_best_k_grid, target_names=['0', '1', '2', '3', '4'])
c_report_random_knn = classification_report(y_test, y_pred_best_random_knn, target_names=['0', '1', '2', '3', '4'])
c_report_bayes_knn = classification_report(y_test, y_pred_best_bayes_knn, target_names=['0', '1', '2', '3', '4'])
print(c_report_grid_knn, c_report_random_knn, c_report_bayes_knn)
precision recall f1-score support
0 0.68 0.77 0.72 65
1 0.72 0.83 0.77 52
2 0.75 0.65 0.70 55
3 0.76 0.61 0.67 56
4 0.66 0.67 0.67 52
accuracy 0.71 280
macro avg 0.71 0.71 0.71 280
weighted avg 0.71 0.71 0.71 280
precision recall f1-score support
0 0.68 0.77 0.72 65
1 0.72 0.83 0.77 52
2 0.75 0.65 0.70 55
3 0.76 0.61 0.67 56
4 0.66 0.67 0.67 52
accuracy 0.71 280
macro avg 0.71 0.71 0.71 280
weighted avg 0.71 0.71 0.71 280
precision recall f1-score support
0 0.68 0.77 0.72 65
1 0.72 0.83 0.77 52
2 0.75 0.65 0.70 55
3 0.76 0.61 0.67 56
4 0.66 0.67 0.67 52
accuracy 0.71 280
macro avg 0.71 0.71 0.71 280
weighted avg 0.71 0.71 0.71 280
After evaluating the models, it is possible to observe that the K-Nearest Neighbors (KNN) classifier produced similar results across different hyperparameter search methods: Grid Search, Random Search, and Bayesian Search. This consistency suggests that the chosen parameter ranges and distributions are well-suited for the KNN model, allowing all three methods to effectively explore the hyperparameter space.
Unlike the Random Forest model, where additional parameters impact the model performance from one search to another, the KNN model primarily relies on the same few pivotal parameters (and this is the reason why I choose to keep always the same across all different search methods) 'n_neighbors', 'metric', 'weights' and the 'algorithm'.
These parameters are critical in determining the KNN model's performance, and thus, they were consistently included in the hyperparameter search space.
Despite the similar results, it's important to note that the KNN classifier's accuracy did not improve significantly beyond a certain point which in accuracy is approximately 71% (more precisely 70.71%).
Therefore to make the comparison with the random forest, I will choose just the KNN with grid search (since this method has explored all the possible combinations).
In particular the precise hyperparameters of KNN with grid search are:
- algorithm: auto
- metric: manhattan
- n_neighbors: 9
- weights: distance
¶
4.3 FINAL MODEL SELECTION
In this section, I am going to compare the performance of the two best models got so far: Random Forest using Bayes Search and KNN using grid search.
Again as I did before I consider three key metrics (in addition to accuracy and confusion matrix already computed for each single method in the above steps):
- precision score;
- recall;
- f1-score.
Moreover, since I had multiple classes as a labels (and not a binary situation) I used the average method 'macro' which gives the same importance to each class (this choice comes from the fact that the classes are well balanced and therefore was useless to give more importance to some specific class).
Finally, I generate classification reports for the two models to provide a detailed breakdown of their performance for each class.
average_method ='macro'
for score in (precision_score, recall_score, f1_score):
rf_final = score(y_test, y_pred_bayes, average=average_method)
knn_final = score(y_test, y_pred_best_k_grid, average=average_method)
print(score.__name__, (rf_final, knn_final))
precision_score (0.7336052824885823, 0.7116550512776928) recall_score (0.72998001998002, 0.7061838161838162) f1_score (0.730589691534106, 0.7052489445803459)
c_report_rf_final = classification_report(y_test, y_pred_bayes, target_names=['0', '1', '2', '3', '4'])
c_report_knn_final = classification_report(y_test, y_pred_best_k_grid, target_names=['0', '1', '2', '3', '4'])
print(c_report_rf_final, c_report_knn_final)
precision recall f1-score support
0 0.72 0.78 0.75 65
1 0.70 0.75 0.72 52
2 0.78 0.76 0.77 55
3 0.78 0.68 0.72 56
4 0.70 0.67 0.69 52
accuracy 0.73 280
macro avg 0.73 0.73 0.73 280
weighted avg 0.73 0.73 0.73 280
precision recall f1-score support
0 0.68 0.77 0.72 65
1 0.72 0.83 0.77 52
2 0.75 0.65 0.70 55
3 0.76 0.61 0.67 56
4 0.66 0.67 0.67 52
accuracy 0.71 280
macro avg 0.71 0.71 0.71 280
weighted avg 0.71 0.71 0.71 280
As it is s possible to notice the Random Forest with Bayes Search overcomes in every metrics the best KNN. Therefore I chose this as the model to predict the final anonymous data. Surely all the score and in particular the accuracy (approximately 73%) are not incredibly satisfying.
¶
4.4 NEURAL NETWORK (EXTRA TOPIC)
I now build a neural network, in order to see if this model can capture better the complexity of our dataset and improve the performance on the metrics (in particular on the accuracy).
For the structure, I chose to include:
- a flatten layer to convert the input data into a one-dimensional array;
- five linear (fully connected) layers separated by Leaky ReLU activation functions. Leaky ReLU introduces non-linearity to the model and often performs better than the traditional ReLU function;
- dropout layers to prevent overfitting by randomly setting a fraction of input units to 0 at each update during training.
- batchNormalization layers between linear layers to normalize the activations of the previous layer, improving the stability and performance of the model.
- a softmax function at the output layer to assign probabilities to each class, enabling multi-class classification.
For training I used:
- cross Entropy loss, which is well-suited for multi-class classification tasks.
- full batch training, meaning the entire dataset is used in each training iteration.
- a large number of epochs (10,000) after experimenting with 1,000 and 15,000 epochs. With 1,000 epochs, the accuracy was lower, while with 15,000 epochs, the model began to overfit.
class NeuralNetwork(nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__()
self.model = nn.Sequential(
nn.Flatten(),
nn.Linear(25, 512), # Input layer adjusted to 25 features
nn.LeakyReLU(),
nn.Dropout(0.4),
nn.Linear(512, 256), # Hidden layer
nn.LeakyReLU(),
nn.BatchNorm1d(256),
nn.Dropout(0.4),
nn.Linear(256, 128), # Hidden layer
nn.LeakyReLU(),
nn.Dropout(0.3),
nn.Linear(128, 64), # Hidden layer
nn.LeakyReLU(),
nn.Linear(64, 5), # Output layer adjusted to 5 classes
nn.Softmax(dim=1) # Softmax activation for multi-class classification
)
def forward(self, x):
return self.model(x)
model_nn = NeuralNetwork()
print(model_nn)
NeuralNetwork(
(model): Sequential(
(0): Flatten(start_dim=1, end_dim=-1)
(1): Linear(in_features=25, out_features=512, bias=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Dropout(p=0.4, inplace=False)
(4): Linear(in_features=512, out_features=256, bias=True)
(5): LeakyReLU(negative_slope=0.01)
(6): BatchNorm1d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.4, inplace=False)
(8): Linear(in_features=256, out_features=128, bias=True)
(9): LeakyReLU(negative_slope=0.01)
(10): Dropout(p=0.3, inplace=False)
(11): Linear(in_features=128, out_features=64, bias=True)
(12): LeakyReLU(negative_slope=0.01)
(13): Linear(in_features=64, out_features=5, bias=True)
(14): Softmax(dim=1)
)
)
X_train_nn, X_val_nn, y_train_nn, y_val_nn = train_test_split(X_train.values, y_train.values, test_size=0.2, random_state=42)
X_train_tensor = torch.tensor(X_train_nn, dtype=torch.float32)
y_train_tensor = torch.tensor(y_train_nn, dtype=torch.long)
X_val_tensor = torch.tensor(X_val_nn, dtype=torch.float32)
y_val_tensor = torch.tensor(y_val_nn, dtype=torch.long)
import torch
import torch.nn as nn
import torch.optim as optim
# Assuming model_DS_H is your NeuralNetworkDropSeq model
# Use CrossEntropyLoss for multi-class classification
criterion = nn.CrossEntropyLoss()
# Use an optimizer (SGD in this case)
optimizer = torch.optim.SGD(model_nn.parameters(), lr=0.01)
epochs = 10000
best_val_acc = 0
patience = 3
no_improve_epochs = 0
best_model_path_nn = 'best_model_final_nn.pth'
for epoch in range(epochs):
model_nn.train()
optimizer.zero_grad() # Reset the gradients of all model parameters to zero.
train_output = model_nn(X_train_tensor) # Forward pass with all training data
train_loss = criterion(train_output, y_train_tensor) # Calculate the loss
train_loss.backward() # Compute the gradients of the loss with respect to the model's parameters
optimizer.step() # Update the weights
# Calculate training accuracy
with torch.no_grad():
train_predictions = torch.argmax(train_output, dim=1) # Get the predicted class indices
train_correct = (train_predictions == y_train_tensor).sum().item()
train_total = y_train_tensor.size(0)
train_acc = train_correct / train_total
# Validation
model_nn.eval() # Set the model to evaluation mode
with torch.no_grad():
val_output = model_nn(X_val_tensor) # Compute predictions on the validation dataset
val_loss = criterion(val_output, y_val_tensor)
val_predictions = torch.argmax(val_output, dim=1) # Get the predicted class indices
val_correct = (val_predictions == y_val_tensor).sum().item()
val_total = y_val_tensor.size(0)
val_acc = val_correct / val_total
print(f'Epoch {epoch+1}/{epochs}, '
f'Train Loss: {train_loss.item():.4f}, '
f'Train Accuracy: {train_acc:.4f}, '
f'Val Loss: {val_loss.item():.4f}, '
f'Val Accuracy: {val_acc:.4f}')
Epoch 1/10000, Train Loss: 1.6105, Train Accuracy: 0.1853, Val Loss: 1.6100, Val Accuracy: 0.1741 Epoch 2/10000, Train Loss: 1.6095, Train Accuracy: 0.1920, Val Loss: 1.6100, Val Accuracy: 0.1741 Epoch 3/10000, Train Loss: 1.6107, Train Accuracy: 0.1942, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 4/10000, Train Loss: 1.6112, Train Accuracy: 0.1853, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 5/10000, Train Loss: 1.6106, Train Accuracy: 0.1875, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 6/10000, Train Loss: 1.6101, Train Accuracy: 0.1897, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 7/10000, Train Loss: 1.6094, Train Accuracy: 0.1998, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 8/10000, Train Loss: 1.6092, Train Accuracy: 0.2009, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 9/10000, Train Loss: 1.6088, Train Accuracy: 0.2042, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 10/10000, Train Loss: 1.6112, Train Accuracy: 0.1864, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 11/10000, Train Loss: 1.6107, Train Accuracy: 0.2009, Val Loss: 1.6100, Val Accuracy: 0.1786 Epoch 12/10000, Train Loss: 1.6100, Train Accuracy: 0.2042, Val Loss: 1.6099, Val Accuracy: 0.1786 Epoch 13/10000, Train Loss: 1.6098, Train Accuracy: 0.1886, Val Loss: 1.6099, Val Accuracy: 0.1786 Epoch 14/10000, Train Loss: 1.6087, Train Accuracy: 0.2054, Val Loss: 1.6099, Val Accuracy: 0.1786 Epoch 15/10000, Train Loss: 1.6105, Train Accuracy: 0.1920, Val Loss: 1.6099, Val Accuracy: 0.1786 Epoch 16/10000, Train Loss: 1.6110, Train Accuracy: 0.1652, Val Loss: 1.6099, Val Accuracy: 0.1786 Epoch 17/10000, Train Loss: 1.6098, Train Accuracy: 0.1998, Val Loss: 1.6099, Val Accuracy: 0.1786 Epoch 18/10000, Train Loss: 1.6108, Train Accuracy: 0.1730, Val Loss: 1.6098, Val Accuracy: 0.1786 Epoch 19/10000, Train Loss: 1.6104, Train Accuracy: 0.1964, Val Loss: 1.6098, Val Accuracy: 0.1786 Epoch 20/10000, Train Loss: 1.6111, Train Accuracy: 0.1908, Val Loss: 1.6098, Val Accuracy: 0.1786 Epoch 21/10000, Train Loss: 1.6097, Train Accuracy: 0.1908, Val Loss: 1.6098, Val Accuracy: 0.1830 Epoch 22/10000, Train Loss: 1.6103, Train Accuracy: 0.2065, Val Loss: 1.6098, Val Accuracy: 0.1830 Epoch 23/10000, Train Loss: 1.6102, Train Accuracy: 0.2054, Val Loss: 1.6097, Val Accuracy: 0.1830 Epoch 24/10000, Train Loss: 1.6099, Train Accuracy: 0.1975, Val Loss: 1.6097, Val Accuracy: 0.1830 Epoch 25/10000, Train Loss: 1.6104, Train Accuracy: 0.1830, Val Loss: 1.6097, Val Accuracy: 0.1830 Epoch 26/10000, Train Loss: 1.6106, Train Accuracy: 0.1741, Val Loss: 1.6097, Val Accuracy: 0.1830 Epoch 27/10000, Train Loss: 1.6110, Train Accuracy: 0.1696, Val Loss: 1.6097, Val Accuracy: 0.1830 Epoch 28/10000, Train Loss: 1.6106, Train Accuracy: 0.1975, Val Loss: 1.6097, Val Accuracy: 0.1830 Epoch 29/10000, Train Loss: 1.6109, Train Accuracy: 0.1864, Val Loss: 1.6096, Val Accuracy: 0.1830 Epoch 30/10000, Train Loss: 1.6107, Train Accuracy: 0.1875, Val Loss: 1.6096, Val Accuracy: 0.1830 Epoch 31/10000, Train Loss: 1.6081, Train Accuracy: 0.2288, Val Loss: 1.6096, Val Accuracy: 0.1830 Epoch 32/10000, Train Loss: 1.6104, Train Accuracy: 0.1842, Val Loss: 1.6096, Val Accuracy: 0.1830 Epoch 33/10000, Train Loss: 1.6094, Train Accuracy: 0.1875, Val Loss: 1.6096, Val Accuracy: 0.1830 Epoch 34/10000, Train Loss: 1.6105, Train Accuracy: 0.2020, Val Loss: 1.6095, Val Accuracy: 0.1786 Epoch 35/10000, Train Loss: 1.6103, Train Accuracy: 0.1897, Val Loss: 1.6095, Val Accuracy: 0.1786 Epoch 36/10000, Train Loss: 1.6100, Train Accuracy: 0.2009, Val Loss: 1.6095, Val Accuracy: 0.1786 Epoch 37/10000, Train Loss: 1.6098, Train Accuracy: 0.1842, Val Loss: 1.6095, Val Accuracy: 0.1786 Epoch 38/10000, Train Loss: 1.6093, Train Accuracy: 0.2054, Val Loss: 1.6095, Val Accuracy: 0.1786 Epoch 39/10000, Train Loss: 1.6098, Train Accuracy: 0.2109, Val Loss: 1.6095, Val Accuracy: 0.1830 Epoch 40/10000, Train Loss: 1.6103, Train Accuracy: 0.1964, Val Loss: 1.6094, Val Accuracy: 0.1830 Epoch 41/10000, Train Loss: 1.6105, Train Accuracy: 0.1987, Val Loss: 1.6094, Val Accuracy: 0.1830 Epoch 42/10000, Train Loss: 1.6106, Train Accuracy: 0.1797, Val Loss: 1.6094, Val Accuracy: 0.1830 Epoch 43/10000, Train Loss: 1.6104, Train Accuracy: 0.1864, Val Loss: 1.6094, Val Accuracy: 0.1830 Epoch 44/10000, Train Loss: 1.6089, Train Accuracy: 0.2020, Val Loss: 1.6094, Val Accuracy: 0.1830 Epoch 45/10000, Train Loss: 1.6096, Train Accuracy: 0.2087, Val Loss: 1.6094, Val Accuracy: 0.1830 Epoch 46/10000, Train Loss: 1.6091, Train Accuracy: 0.2098, Val Loss: 1.6093, Val Accuracy: 0.1830 Epoch 47/10000, Train Loss: 1.6095, Train Accuracy: 0.2031, Val Loss: 1.6093, Val Accuracy: 0.1830 Epoch 48/10000, Train Loss: 1.6092, Train Accuracy: 0.2121, Val Loss: 1.6093, Val Accuracy: 0.1830 Epoch 49/10000, Train Loss: 1.6097, Train Accuracy: 0.2121, Val Loss: 1.6093, Val Accuracy: 0.1830 Epoch 50/10000, Train Loss: 1.6084, Train Accuracy: 0.2087, Val Loss: 1.6093, Val Accuracy: 0.1875 Epoch 51/10000, Train Loss: 1.6096, Train Accuracy: 0.2109, Val Loss: 1.6093, Val Accuracy: 0.1875 Epoch 52/10000, Train Loss: 1.6085, Train Accuracy: 0.2121, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 53/10000, Train Loss: 1.6099, Train Accuracy: 0.1953, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 54/10000, Train Loss: 1.6091, Train Accuracy: 0.2065, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 55/10000, Train Loss: 1.6086, Train Accuracy: 0.2098, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 56/10000, Train Loss: 1.6092, Train Accuracy: 0.1998, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 57/10000, Train Loss: 1.6101, Train Accuracy: 0.1875, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 58/10000, Train Loss: 1.6104, Train Accuracy: 0.1987, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 59/10000, Train Loss: 1.6095, Train Accuracy: 0.1975, Val Loss: 1.6092, Val Accuracy: 0.1875 Epoch 60/10000, Train Loss: 1.6089, Train Accuracy: 0.1975, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 61/10000, Train Loss: 1.6091, Train Accuracy: 0.2221, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 62/10000, Train Loss: 1.6086, Train Accuracy: 0.2031, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 63/10000, Train Loss: 1.6092, Train Accuracy: 0.2020, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 64/10000, Train Loss: 1.6091, Train Accuracy: 0.2031, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 65/10000, Train Loss: 1.6098, Train Accuracy: 0.1886, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 66/10000, Train Loss: 1.6088, Train Accuracy: 0.2020, Val Loss: 1.6091, Val Accuracy: 0.1875 Epoch 67/10000, Train Loss: 1.6096, Train Accuracy: 0.2154, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 68/10000, Train Loss: 1.6079, Train Accuracy: 0.2031, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 69/10000, Train Loss: 1.6093, Train Accuracy: 0.1998, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 70/10000, Train Loss: 1.6104, Train Accuracy: 0.1920, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 71/10000, Train Loss: 1.6090, Train Accuracy: 0.2232, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 72/10000, Train Loss: 1.6096, Train Accuracy: 0.1931, Val Loss: 1.6090, Val Accuracy: 0.1920 Epoch 73/10000, Train Loss: 1.6098, Train Accuracy: 0.1975, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 74/10000, Train Loss: 1.6097, Train Accuracy: 0.2076, Val Loss: 1.6090, Val Accuracy: 0.1875 Epoch 75/10000, Train Loss: 1.6098, Train Accuracy: 0.2098, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 76/10000, Train Loss: 1.6087, Train Accuracy: 0.2098, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 77/10000, Train Loss: 1.6095, Train Accuracy: 0.1897, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 78/10000, Train Loss: 1.6090, Train Accuracy: 0.2065, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 79/10000, Train Loss: 1.6101, Train Accuracy: 0.2042, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 80/10000, Train Loss: 1.6099, Train Accuracy: 0.2065, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 81/10000, Train Loss: 1.6095, Train Accuracy: 0.1931, Val Loss: 1.6089, Val Accuracy: 0.1920 Epoch 82/10000, Train Loss: 1.6099, Train Accuracy: 0.2009, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 83/10000, Train Loss: 1.6086, Train Accuracy: 0.2232, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 84/10000, Train Loss: 1.6088, Train Accuracy: 0.2143, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 85/10000, Train Loss: 1.6094, Train Accuracy: 0.2121, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 86/10000, Train Loss: 1.6089, Train Accuracy: 0.2076, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 87/10000, Train Loss: 1.6090, Train Accuracy: 0.1953, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 88/10000, Train Loss: 1.6089, Train Accuracy: 0.2076, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 89/10000, Train Loss: 1.6093, Train Accuracy: 0.2176, Val Loss: 1.6088, Val Accuracy: 0.1920 Epoch 90/10000, Train Loss: 1.6094, Train Accuracy: 0.2109, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 91/10000, Train Loss: 1.6082, Train Accuracy: 0.2065, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 92/10000, Train Loss: 1.6093, Train Accuracy: 0.2042, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 93/10000, Train Loss: 1.6081, Train Accuracy: 0.2221, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 94/10000, Train Loss: 1.6073, Train Accuracy: 0.2020, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 95/10000, Train Loss: 1.6086, Train Accuracy: 0.2098, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 96/10000, Train Loss: 1.6079, Train Accuracy: 0.2288, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 97/10000, Train Loss: 1.6096, Train Accuracy: 0.1953, Val Loss: 1.6087, Val Accuracy: 0.1920 Epoch 98/10000, Train Loss: 1.6086, Train Accuracy: 0.2143, Val Loss: 1.6086, Val Accuracy: 0.1920 Epoch 99/10000, Train Loss: 1.6085, Train Accuracy: 0.2188, Val Loss: 1.6086, Val Accuracy: 0.1920 Epoch 100/10000, Train Loss: 1.6098, Train Accuracy: 0.1987, Val Loss: 1.6086, Val Accuracy: 0.1920 Epoch 101/10000, Train Loss: 1.6099, Train Accuracy: 0.1953, Val Loss: 1.6086, Val Accuracy: 0.1964 Epoch 102/10000, Train Loss: 1.6087, Train Accuracy: 0.2176, Val Loss: 1.6086, Val Accuracy: 0.1964 Epoch 103/10000, Train Loss: 1.6086, Train Accuracy: 0.2188, Val Loss: 1.6086, Val Accuracy: 0.1964 Epoch 104/10000, Train Loss: 1.6078, Train Accuracy: 0.2176, Val Loss: 1.6086, Val Accuracy: 0.1964 Epoch 105/10000, Train Loss: 1.6085, Train Accuracy: 0.2299, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 106/10000, Train Loss: 1.6093, Train Accuracy: 0.1886, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 107/10000, Train Loss: 1.6076, Train Accuracy: 0.2254, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 108/10000, Train Loss: 1.6087, Train Accuracy: 0.2221, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 109/10000, Train Loss: 1.6084, Train Accuracy: 0.2121, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 110/10000, Train Loss: 1.6090, Train Accuracy: 0.1920, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 111/10000, Train Loss: 1.6078, Train Accuracy: 0.2221, Val Loss: 1.6085, Val Accuracy: 0.1964 Epoch 112/10000, Train Loss: 1.6085, Train Accuracy: 0.2188, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 113/10000, Train Loss: 1.6092, Train Accuracy: 0.2087, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 114/10000, Train Loss: 1.6091, Train Accuracy: 0.1942, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 115/10000, Train Loss: 1.6080, Train Accuracy: 0.2143, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 116/10000, Train Loss: 1.6083, Train Accuracy: 0.2143, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 117/10000, Train Loss: 1.6084, Train Accuracy: 0.2076, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 118/10000, Train Loss: 1.6081, Train Accuracy: 0.2154, Val Loss: 1.6084, Val Accuracy: 0.1964 Epoch 119/10000, Train Loss: 1.6080, Train Accuracy: 0.2333, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 120/10000, Train Loss: 1.6085, Train Accuracy: 0.1953, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 121/10000, Train Loss: 1.6074, Train Accuracy: 0.2199, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 122/10000, Train Loss: 1.6097, Train Accuracy: 0.1975, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 123/10000, Train Loss: 1.6086, Train Accuracy: 0.2221, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 124/10000, Train Loss: 1.6084, Train Accuracy: 0.2176, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 125/10000, Train Loss: 1.6084, Train Accuracy: 0.2210, Val Loss: 1.6083, Val Accuracy: 0.1964 Epoch 126/10000, Train Loss: 1.6081, Train Accuracy: 0.1942, Val Loss: 1.6082, Val Accuracy: 0.1964 Epoch 127/10000, Train Loss: 1.6078, Train Accuracy: 0.2143, Val Loss: 1.6082, Val Accuracy: 0.1964 Epoch 128/10000, Train Loss: 1.6088, Train Accuracy: 0.2121, Val Loss: 1.6082, Val Accuracy: 0.2009 Epoch 129/10000, Train Loss: 1.6076, Train Accuracy: 0.2288, Val Loss: 1.6082, Val Accuracy: 0.2009 Epoch 130/10000, Train Loss: 1.6075, Train Accuracy: 0.2054, Val Loss: 1.6082, Val Accuracy: 0.2009 Epoch 131/10000, Train Loss: 1.6077, Train Accuracy: 0.2299, Val Loss: 1.6082, Val Accuracy: 0.2009 Epoch 132/10000, Train Loss: 1.6082, Train Accuracy: 0.2009, Val Loss: 1.6082, Val Accuracy: 0.2054 Epoch 133/10000, Train Loss: 1.6081, Train Accuracy: 0.2109, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 134/10000, Train Loss: 1.6089, Train Accuracy: 0.2310, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 135/10000, Train Loss: 1.6086, Train Accuracy: 0.2199, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 136/10000, Train Loss: 1.6085, Train Accuracy: 0.2121, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 137/10000, Train Loss: 1.6087, Train Accuracy: 0.2199, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 138/10000, Train Loss: 1.6083, Train Accuracy: 0.2154, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 139/10000, Train Loss: 1.6083, Train Accuracy: 0.2388, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 140/10000, Train Loss: 1.6084, Train Accuracy: 0.2288, Val Loss: 1.6081, Val Accuracy: 0.2054 Epoch 141/10000, Train Loss: 1.6083, Train Accuracy: 0.2188, Val Loss: 1.6080, Val Accuracy: 0.2054 Epoch 142/10000, Train Loss: 1.6077, Train Accuracy: 0.2176, Val Loss: 1.6080, Val Accuracy: 0.2054 Epoch 143/10000, Train Loss: 1.6075, Train Accuracy: 0.2210, Val Loss: 1.6080, Val Accuracy: 0.2054 Epoch 144/10000, Train Loss: 1.6083, Train Accuracy: 0.2165, Val Loss: 1.6080, Val Accuracy: 0.2054 Epoch 145/10000, Train Loss: 1.6085, Train Accuracy: 0.2165, Val Loss: 1.6080, Val Accuracy: 0.2054 Epoch 146/10000, Train Loss: 1.6073, Train Accuracy: 0.2254, Val Loss: 1.6080, Val Accuracy: 0.2054 Epoch 147/10000, Train Loss: 1.6086, Train Accuracy: 0.2266, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 148/10000, Train Loss: 1.6067, Train Accuracy: 0.2299, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 149/10000, Train Loss: 1.6082, Train Accuracy: 0.2121, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 150/10000, Train Loss: 1.6074, Train Accuracy: 0.2433, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 151/10000, Train Loss: 1.6076, Train Accuracy: 0.2098, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 152/10000, Train Loss: 1.6067, Train Accuracy: 0.2556, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 153/10000, Train Loss: 1.6074, Train Accuracy: 0.2154, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 154/10000, Train Loss: 1.6080, Train Accuracy: 0.2221, Val Loss: 1.6079, Val Accuracy: 0.2054 Epoch 155/10000, Train Loss: 1.6077, Train Accuracy: 0.2188, Val Loss: 1.6078, Val Accuracy: 0.2054 Epoch 156/10000, Train Loss: 1.6077, Train Accuracy: 0.2154, Val Loss: 1.6078, Val Accuracy: 0.2054 Epoch 157/10000, Train Loss: 1.6077, Train Accuracy: 0.2109, Val Loss: 1.6078, Val Accuracy: 0.2054 Epoch 158/10000, Train Loss: 1.6073, Train Accuracy: 0.2154, Val Loss: 1.6078, Val Accuracy: 0.2054 Epoch 159/10000, Train Loss: 1.6080, Train Accuracy: 0.2210, Val Loss: 1.6078, Val Accuracy: 0.2054 Epoch 160/10000, Train Loss: 1.6087, Train Accuracy: 0.2165, Val Loss: 1.6078, Val Accuracy: 0.2098 Epoch 161/10000, Train Loss: 1.6071, Train Accuracy: 0.2355, Val Loss: 1.6078, Val Accuracy: 0.2098 Epoch 162/10000, Train Loss: 1.6088, Train Accuracy: 0.1987, Val Loss: 1.6078, Val Accuracy: 0.2098 Epoch 163/10000, Train Loss: 1.6080, Train Accuracy: 0.2176, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 164/10000, Train Loss: 1.6080, Train Accuracy: 0.2232, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 165/10000, Train Loss: 1.6071, Train Accuracy: 0.2165, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 166/10000, Train Loss: 1.6087, Train Accuracy: 0.2221, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 167/10000, Train Loss: 1.6083, Train Accuracy: 0.2121, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 168/10000, Train Loss: 1.6067, Train Accuracy: 0.2321, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 169/10000, Train Loss: 1.6075, Train Accuracy: 0.2232, Val Loss: 1.6077, Val Accuracy: 0.2143 Epoch 170/10000, Train Loss: 1.6082, Train Accuracy: 0.2299, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 171/10000, Train Loss: 1.6070, Train Accuracy: 0.2277, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 172/10000, Train Loss: 1.6068, Train Accuracy: 0.2143, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 173/10000, Train Loss: 1.6071, Train Accuracy: 0.2277, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 174/10000, Train Loss: 1.6083, Train Accuracy: 0.2121, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 175/10000, Train Loss: 1.6079, Train Accuracy: 0.2210, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 176/10000, Train Loss: 1.6082, Train Accuracy: 0.2254, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 177/10000, Train Loss: 1.6073, Train Accuracy: 0.2388, Val Loss: 1.6076, Val Accuracy: 0.2143 Epoch 178/10000, Train Loss: 1.6067, Train Accuracy: 0.2288, Val Loss: 1.6075, Val Accuracy: 0.2143 Epoch 179/10000, Train Loss: 1.6075, Train Accuracy: 0.2288, Val Loss: 1.6075, Val Accuracy: 0.2143 Epoch 180/10000, Train Loss: 1.6080, Train Accuracy: 0.2310, Val Loss: 1.6075, Val Accuracy: 0.2143 Epoch 181/10000, Train Loss: 1.6066, Train Accuracy: 0.2366, Val Loss: 1.6075, Val Accuracy: 0.2143 Epoch 182/10000, Train Loss: 1.6087, Train Accuracy: 0.2076, Val Loss: 1.6075, Val Accuracy: 0.2143 Epoch 183/10000, Train Loss: 1.6076, Train Accuracy: 0.2076, Val Loss: 1.6075, Val Accuracy: 0.2143 Epoch 184/10000, Train Loss: 1.6074, Train Accuracy: 0.2132, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 185/10000, Train Loss: 1.6061, Train Accuracy: 0.2288, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 186/10000, Train Loss: 1.6072, Train Accuracy: 0.2221, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 187/10000, Train Loss: 1.6075, Train Accuracy: 0.2254, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 188/10000, Train Loss: 1.6071, Train Accuracy: 0.2377, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 189/10000, Train Loss: 1.6077, Train Accuracy: 0.2455, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 190/10000, Train Loss: 1.6062, Train Accuracy: 0.2388, Val Loss: 1.6074, Val Accuracy: 0.2143 Epoch 191/10000, Train Loss: 1.6083, Train Accuracy: 0.2355, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 192/10000, Train Loss: 1.6070, Train Accuracy: 0.2176, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 193/10000, Train Loss: 1.6075, Train Accuracy: 0.2266, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 194/10000, Train Loss: 1.6077, Train Accuracy: 0.2388, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 195/10000, Train Loss: 1.6071, Train Accuracy: 0.2266, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 196/10000, Train Loss: 1.6062, Train Accuracy: 0.2400, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 197/10000, Train Loss: 1.6079, Train Accuracy: 0.2042, Val Loss: 1.6073, Val Accuracy: 0.2143 Epoch 198/10000, Train Loss: 1.6063, Train Accuracy: 0.2455, Val Loss: 1.6072, Val Accuracy: 0.2143 Epoch 199/10000, Train Loss: 1.6062, Train Accuracy: 0.2277, Val Loss: 1.6072, Val Accuracy: 0.2143 Epoch 200/10000, Train Loss: 1.6076, Train Accuracy: 0.2243, Val Loss: 1.6072, Val Accuracy: 0.2143 Epoch 201/10000, Train Loss: 1.6069, Train Accuracy: 0.2243, Val Loss: 1.6072, Val Accuracy: 0.2143 Epoch 202/10000, Train Loss: 1.6073, Train Accuracy: 0.2243, Val Loss: 1.6072, Val Accuracy: 0.2143 Epoch 203/10000, Train Loss: 1.6064, Train Accuracy: 0.2444, Val Loss: 1.6072, Val Accuracy: 0.2188 Epoch 204/10000, Train Loss: 1.6074, Train Accuracy: 0.2243, Val Loss: 1.6072, Val Accuracy: 0.2143 Epoch 205/10000, Train Loss: 1.6066, Train Accuracy: 0.2355, Val Loss: 1.6071, Val Accuracy: 0.2143 Epoch 206/10000, Train Loss: 1.6075, Train Accuracy: 0.2143, Val Loss: 1.6071, Val Accuracy: 0.2188 Epoch 207/10000, Train Loss: 1.6068, Train Accuracy: 0.2422, Val Loss: 1.6071, Val Accuracy: 0.2188 Epoch 208/10000, Train Loss: 1.6069, Train Accuracy: 0.2254, Val Loss: 1.6071, Val Accuracy: 0.2188 Epoch 209/10000, Train Loss: 1.6078, Train Accuracy: 0.2266, Val Loss: 1.6071, Val Accuracy: 0.2188 Epoch 210/10000, Train Loss: 1.6076, Train Accuracy: 0.2121, Val Loss: 1.6071, Val Accuracy: 0.2188 Epoch 211/10000, Train Loss: 1.6074, Train Accuracy: 0.2020, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 212/10000, Train Loss: 1.6069, Train Accuracy: 0.2299, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 213/10000, Train Loss: 1.6071, Train Accuracy: 0.2444, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 214/10000, Train Loss: 1.6068, Train Accuracy: 0.2243, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 215/10000, Train Loss: 1.6071, Train Accuracy: 0.2299, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 216/10000, Train Loss: 1.6064, Train Accuracy: 0.2221, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 217/10000, Train Loss: 1.6069, Train Accuracy: 0.2377, Val Loss: 1.6070, Val Accuracy: 0.2188 Epoch 218/10000, Train Loss: 1.6062, Train Accuracy: 0.2132, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 219/10000, Train Loss: 1.6059, Train Accuracy: 0.2388, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 220/10000, Train Loss: 1.6069, Train Accuracy: 0.2254, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 221/10000, Train Loss: 1.6063, Train Accuracy: 0.2455, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 222/10000, Train Loss: 1.6074, Train Accuracy: 0.2344, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 223/10000, Train Loss: 1.6055, Train Accuracy: 0.2455, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 224/10000, Train Loss: 1.6065, Train Accuracy: 0.2277, Val Loss: 1.6069, Val Accuracy: 0.2188 Epoch 225/10000, Train Loss: 1.6068, Train Accuracy: 0.2333, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 226/10000, Train Loss: 1.6071, Train Accuracy: 0.2154, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 227/10000, Train Loss: 1.6066, Train Accuracy: 0.2411, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 228/10000, Train Loss: 1.6070, Train Accuracy: 0.2310, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 229/10000, Train Loss: 1.6070, Train Accuracy: 0.2321, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 230/10000, Train Loss: 1.6080, Train Accuracy: 0.2344, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 231/10000, Train Loss: 1.6064, Train Accuracy: 0.2400, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 232/10000, Train Loss: 1.6059, Train Accuracy: 0.2433, Val Loss: 1.6068, Val Accuracy: 0.2188 Epoch 233/10000, Train Loss: 1.6070, Train Accuracy: 0.2411, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 234/10000, Train Loss: 1.6063, Train Accuracy: 0.2422, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 235/10000, Train Loss: 1.6075, Train Accuracy: 0.2165, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 236/10000, Train Loss: 1.6066, Train Accuracy: 0.2355, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 237/10000, Train Loss: 1.6073, Train Accuracy: 0.2299, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 238/10000, Train Loss: 1.6070, Train Accuracy: 0.2310, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 239/10000, Train Loss: 1.6073, Train Accuracy: 0.2310, Val Loss: 1.6067, Val Accuracy: 0.2188 Epoch 240/10000, Train Loss: 1.6065, Train Accuracy: 0.2444, Val Loss: 1.6066, Val Accuracy: 0.2188 Epoch 241/10000, Train Loss: 1.6071, Train Accuracy: 0.2277, Val Loss: 1.6066, Val Accuracy: 0.2188 Epoch 242/10000, Train Loss: 1.6066, Train Accuracy: 0.2522, Val Loss: 1.6066, Val Accuracy: 0.2188 Epoch 243/10000, Train Loss: 1.6061, Train Accuracy: 0.2511, Val Loss: 1.6066, Val Accuracy: 0.2188 Epoch 244/10000, Train Loss: 1.6061, Train Accuracy: 0.2589, Val Loss: 1.6066, Val Accuracy: 0.2188 Epoch 245/10000, Train Loss: 1.6052, Train Accuracy: 0.2556, Val Loss: 1.6065, Val Accuracy: 0.2188 Epoch 246/10000, Train Loss: 1.6053, Train Accuracy: 0.2500, Val Loss: 1.6065, Val Accuracy: 0.2188 Epoch 247/10000, Train Loss: 1.6061, Train Accuracy: 0.2333, Val Loss: 1.6065, Val Accuracy: 0.2188 Epoch 248/10000, Train Loss: 1.6080, Train Accuracy: 0.2210, Val Loss: 1.6065, Val Accuracy: 0.2188 Epoch 249/10000, Train Loss: 1.6072, Train Accuracy: 0.2344, Val Loss: 1.6065, Val Accuracy: 0.2188 Epoch 250/10000, Train Loss: 1.6064, Train Accuracy: 0.2344, Val Loss: 1.6065, Val Accuracy: 0.2232 Epoch 251/10000, Train Loss: 1.6065, Train Accuracy: 0.2478, Val Loss: 1.6065, Val Accuracy: 0.2232 Epoch 252/10000, Train Loss: 1.6060, Train Accuracy: 0.2489, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 253/10000, Train Loss: 1.6068, Train Accuracy: 0.2478, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 254/10000, Train Loss: 1.6054, Train Accuracy: 0.2600, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 255/10000, Train Loss: 1.6071, Train Accuracy: 0.2310, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 256/10000, Train Loss: 1.6064, Train Accuracy: 0.2243, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 257/10000, Train Loss: 1.6053, Train Accuracy: 0.2578, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 258/10000, Train Loss: 1.6052, Train Accuracy: 0.2422, Val Loss: 1.6064, Val Accuracy: 0.2232 Epoch 259/10000, Train Loss: 1.6057, Train Accuracy: 0.2478, Val Loss: 1.6063, Val Accuracy: 0.2232 Epoch 260/10000, Train Loss: 1.6064, Train Accuracy: 0.2478, Val Loss: 1.6063, Val Accuracy: 0.2232 Epoch 261/10000, Train Loss: 1.6052, Train Accuracy: 0.2567, Val Loss: 1.6063, Val Accuracy: 0.2232 Epoch 262/10000, Train Loss: 1.6056, Train Accuracy: 0.2511, Val Loss: 1.6063, Val Accuracy: 0.2232 Epoch 263/10000, Train Loss: 1.6060, Train Accuracy: 0.2388, Val Loss: 1.6063, Val Accuracy: 0.2232 Epoch 264/10000, Train Loss: 1.6059, Train Accuracy: 0.2455, Val Loss: 1.6063, Val Accuracy: 0.2232 Epoch 265/10000, Train Loss: 1.6057, Train Accuracy: 0.2467, Val Loss: 1.6063, Val Accuracy: 0.2277 Epoch 266/10000, Train Loss: 1.6074, Train Accuracy: 0.2299, Val Loss: 1.6062, Val Accuracy: 0.2277 Epoch 267/10000, Train Loss: 1.6055, Train Accuracy: 0.2344, Val Loss: 1.6062, Val Accuracy: 0.2277 Epoch 268/10000, Train Loss: 1.6061, Train Accuracy: 0.2266, Val Loss: 1.6062, Val Accuracy: 0.2277 Epoch 269/10000, Train Loss: 1.6064, Train Accuracy: 0.2366, Val Loss: 1.6062, Val Accuracy: 0.2232 Epoch 270/10000, Train Loss: 1.6060, Train Accuracy: 0.2333, Val Loss: 1.6062, Val Accuracy: 0.2232 Epoch 271/10000, Train Loss: 1.6049, Train Accuracy: 0.2522, Val Loss: 1.6062, Val Accuracy: 0.2277 Epoch 272/10000, Train Loss: 1.6058, Train Accuracy: 0.2500, Val Loss: 1.6061, Val Accuracy: 0.2232 Epoch 273/10000, Train Loss: 1.6057, Train Accuracy: 0.2254, Val Loss: 1.6061, Val Accuracy: 0.2277 Epoch 274/10000, Train Loss: 1.6063, Train Accuracy: 0.2600, Val Loss: 1.6061, Val Accuracy: 0.2277 Epoch 275/10000, Train Loss: 1.6059, Train Accuracy: 0.2433, Val Loss: 1.6061, Val Accuracy: 0.2232 Epoch 276/10000, Train Loss: 1.6068, Train Accuracy: 0.2344, Val Loss: 1.6061, Val Accuracy: 0.2277 Epoch 277/10000, Train Loss: 1.6064, Train Accuracy: 0.2321, Val Loss: 1.6061, Val Accuracy: 0.2232 Epoch 278/10000, Train Loss: 1.6066, Train Accuracy: 0.2254, Val Loss: 1.6061, Val Accuracy: 0.2232 Epoch 279/10000, Train Loss: 1.6059, Train Accuracy: 0.2377, Val Loss: 1.6060, Val Accuracy: 0.2232 Epoch 280/10000, Train Loss: 1.6058, Train Accuracy: 0.2299, Val Loss: 1.6060, Val Accuracy: 0.2232 Epoch 281/10000, Train Loss: 1.6051, Train Accuracy: 0.2578, Val Loss: 1.6060, Val Accuracy: 0.2232 Epoch 282/10000, Train Loss: 1.6058, Train Accuracy: 0.2210, Val Loss: 1.6060, Val Accuracy: 0.2232 Epoch 283/10000, Train Loss: 1.6050, Train Accuracy: 0.2623, Val Loss: 1.6060, Val Accuracy: 0.2232 Epoch 284/10000, Train Loss: 1.6046, Train Accuracy: 0.2545, Val Loss: 1.6060, Val Accuracy: 0.2232 Epoch 285/10000, Train Loss: 1.6055, Train Accuracy: 0.2578, Val Loss: 1.6059, Val Accuracy: 0.2232 Epoch 286/10000, Train Loss: 1.6057, Train Accuracy: 0.2467, Val Loss: 1.6059, Val Accuracy: 0.2232 Epoch 287/10000, Train Loss: 1.6058, Train Accuracy: 0.2500, Val Loss: 1.6059, Val Accuracy: 0.2232 Epoch 288/10000, Train Loss: 1.6054, Train Accuracy: 0.2533, Val Loss: 1.6059, Val Accuracy: 0.2232 Epoch 289/10000, Train Loss: 1.6058, Train Accuracy: 0.2600, Val Loss: 1.6059, Val Accuracy: 0.2232 Epoch 290/10000, Train Loss: 1.6051, Train Accuracy: 0.2500, Val Loss: 1.6059, Val Accuracy: 0.2232 Epoch 291/10000, Train Loss: 1.6059, Train Accuracy: 0.2310, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 292/10000, Train Loss: 1.6054, Train Accuracy: 0.2310, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 293/10000, Train Loss: 1.6042, Train Accuracy: 0.2634, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 294/10000, Train Loss: 1.6057, Train Accuracy: 0.2377, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 295/10000, Train Loss: 1.6056, Train Accuracy: 0.2355, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 296/10000, Train Loss: 1.6059, Train Accuracy: 0.2288, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 297/10000, Train Loss: 1.6055, Train Accuracy: 0.2377, Val Loss: 1.6058, Val Accuracy: 0.2232 Epoch 298/10000, Train Loss: 1.6063, Train Accuracy: 0.2422, Val Loss: 1.6057, Val Accuracy: 0.2232 Epoch 299/10000, Train Loss: 1.6059, Train Accuracy: 0.2634, Val Loss: 1.6057, Val Accuracy: 0.2232 Epoch 300/10000, Train Loss: 1.6066, Train Accuracy: 0.2377, Val Loss: 1.6057, Val Accuracy: 0.2232 Epoch 301/10000, Train Loss: 1.6042, Train Accuracy: 0.2623, Val Loss: 1.6057, Val Accuracy: 0.2277 Epoch 302/10000, Train Loss: 1.6061, Train Accuracy: 0.2511, Val Loss: 1.6057, Val Accuracy: 0.2277 Epoch 303/10000, Train Loss: 1.6053, Train Accuracy: 0.2533, Val Loss: 1.6057, Val Accuracy: 0.2277 Epoch 304/10000, Train Loss: 1.6061, Train Accuracy: 0.2321, Val Loss: 1.6056, Val Accuracy: 0.2277 Epoch 305/10000, Train Loss: 1.6062, Train Accuracy: 0.2433, Val Loss: 1.6056, Val Accuracy: 0.2277 Epoch 306/10000, Train Loss: 1.6060, Train Accuracy: 0.2299, Val Loss: 1.6056, Val Accuracy: 0.2277 Epoch 307/10000, Train Loss: 1.6056, Train Accuracy: 0.2422, Val Loss: 1.6056, Val Accuracy: 0.2277 Epoch 308/10000, Train Loss: 1.6057, Train Accuracy: 0.2400, Val Loss: 1.6056, Val Accuracy: 0.2277 Epoch 309/10000, Train Loss: 1.6059, Train Accuracy: 0.2511, Val Loss: 1.6056, Val Accuracy: 0.2321 Epoch 310/10000, Train Loss: 1.6041, Train Accuracy: 0.2768, Val Loss: 1.6055, Val Accuracy: 0.2321 Epoch 311/10000, Train Loss: 1.6043, Train Accuracy: 0.2667, Val Loss: 1.6055, Val Accuracy: 0.2321 Epoch 312/10000, Train Loss: 1.6065, Train Accuracy: 0.2433, Val Loss: 1.6055, Val Accuracy: 0.2321 Epoch 313/10000, Train Loss: 1.6048, Train Accuracy: 0.2589, Val Loss: 1.6055, Val Accuracy: 0.2321 Epoch 314/10000, Train Loss: 1.6051, Train Accuracy: 0.2478, Val Loss: 1.6055, Val Accuracy: 0.2321 Epoch 315/10000, Train Loss: 1.6044, Train Accuracy: 0.2522, Val Loss: 1.6055, Val Accuracy: 0.2321 Epoch 316/10000, Train Loss: 1.6048, Train Accuracy: 0.2388, Val Loss: 1.6054, Val Accuracy: 0.2321 Epoch 317/10000, Train Loss: 1.6046, Train Accuracy: 0.2645, Val Loss: 1.6054, Val Accuracy: 0.2321 Epoch 318/10000, Train Loss: 1.6046, Train Accuracy: 0.2589, Val Loss: 1.6054, Val Accuracy: 0.2321 Epoch 319/10000, Train Loss: 1.6039, Train Accuracy: 0.2589, Val Loss: 1.6054, Val Accuracy: 0.2321 Epoch 320/10000, Train Loss: 1.6034, Train Accuracy: 0.2623, Val Loss: 1.6054, Val Accuracy: 0.2321 Epoch 321/10000, Train Loss: 1.6050, Train Accuracy: 0.2589, Val Loss: 1.6054, Val Accuracy: 0.2277 Epoch 322/10000, Train Loss: 1.6055, Train Accuracy: 0.2455, Val Loss: 1.6054, Val Accuracy: 0.2277 Epoch 323/10000, Train Loss: 1.6049, Train Accuracy: 0.2701, Val Loss: 1.6053, Val Accuracy: 0.2277 Epoch 324/10000, Train Loss: 1.6051, Train Accuracy: 0.2467, Val Loss: 1.6053, Val Accuracy: 0.2277 Epoch 325/10000, Train Loss: 1.6059, Train Accuracy: 0.2545, Val Loss: 1.6053, Val Accuracy: 0.2366 Epoch 326/10000, Train Loss: 1.6046, Train Accuracy: 0.2556, Val Loss: 1.6053, Val Accuracy: 0.2366 Epoch 327/10000, Train Loss: 1.6063, Train Accuracy: 0.2411, Val Loss: 1.6053, Val Accuracy: 0.2366 Epoch 328/10000, Train Loss: 1.6056, Train Accuracy: 0.2433, Val Loss: 1.6053, Val Accuracy: 0.2321 Epoch 329/10000, Train Loss: 1.6049, Train Accuracy: 0.2511, Val Loss: 1.6052, Val Accuracy: 0.2366 Epoch 330/10000, Train Loss: 1.6047, Train Accuracy: 0.2768, Val Loss: 1.6052, Val Accuracy: 0.2366 Epoch 331/10000, Train Loss: 1.6056, Train Accuracy: 0.2411, Val Loss: 1.6052, Val Accuracy: 0.2366 Epoch 332/10000, Train Loss: 1.6054, Train Accuracy: 0.2444, Val Loss: 1.6052, Val Accuracy: 0.2366 Epoch 333/10000, Train Loss: 1.6050, Train Accuracy: 0.2377, Val Loss: 1.6052, Val Accuracy: 0.2366 Epoch 334/10000, Train Loss: 1.6055, Train Accuracy: 0.2377, Val Loss: 1.6051, Val Accuracy: 0.2366 Epoch 335/10000, Train Loss: 1.6065, Train Accuracy: 0.2388, Val Loss: 1.6051, Val Accuracy: 0.2366 Epoch 336/10000, Train Loss: 1.6048, Train Accuracy: 0.2478, Val Loss: 1.6051, Val Accuracy: 0.2366 Epoch 337/10000, Train Loss: 1.6044, Train Accuracy: 0.2567, Val Loss: 1.6051, Val Accuracy: 0.2366 Epoch 338/10000, Train Loss: 1.6040, Train Accuracy: 0.2701, Val Loss: 1.6051, Val Accuracy: 0.2366 Epoch 339/10000, Train Loss: 1.6051, Train Accuracy: 0.2422, Val Loss: 1.6051, Val Accuracy: 0.2366 Epoch 340/10000, Train Loss: 1.6051, Train Accuracy: 0.2746, Val Loss: 1.6050, Val Accuracy: 0.2366 Epoch 341/10000, Train Loss: 1.6045, Train Accuracy: 0.2567, Val Loss: 1.6050, Val Accuracy: 0.2411 Epoch 342/10000, Train Loss: 1.6046, Train Accuracy: 0.2567, Val Loss: 1.6050, Val Accuracy: 0.2455 Epoch 343/10000, Train Loss: 1.6029, Train Accuracy: 0.2600, Val Loss: 1.6050, Val Accuracy: 0.2455 Epoch 344/10000, Train Loss: 1.6039, Train Accuracy: 0.2667, Val Loss: 1.6050, Val Accuracy: 0.2455 Epoch 345/10000, Train Loss: 1.6062, Train Accuracy: 0.2511, Val Loss: 1.6050, Val Accuracy: 0.2500 Epoch 346/10000, Train Loss: 1.6036, Train Accuracy: 0.2444, Val Loss: 1.6050, Val Accuracy: 0.2455 Epoch 347/10000, Train Loss: 1.6041, Train Accuracy: 0.2600, Val Loss: 1.6049, Val Accuracy: 0.2500 Epoch 348/10000, Train Loss: 1.6048, Train Accuracy: 0.2723, Val Loss: 1.6049, Val Accuracy: 0.2500 Epoch 349/10000, Train Loss: 1.6055, Train Accuracy: 0.2545, Val Loss: 1.6049, Val Accuracy: 0.2500 Epoch 350/10000, Train Loss: 1.6054, Train Accuracy: 0.2366, Val Loss: 1.6049, Val Accuracy: 0.2500 Epoch 351/10000, Train Loss: 1.6058, Train Accuracy: 0.2567, Val Loss: 1.6049, Val Accuracy: 0.2500 Epoch 352/10000, Train Loss: 1.6032, Train Accuracy: 0.2757, Val Loss: 1.6049, Val Accuracy: 0.2500 Epoch 353/10000, Train Loss: 1.6052, Train Accuracy: 0.2645, Val Loss: 1.6049, Val Accuracy: 0.2545 Epoch 354/10000, Train Loss: 1.6037, Train Accuracy: 0.2690, Val Loss: 1.6048, Val Accuracy: 0.2500 Epoch 355/10000, Train Loss: 1.6050, Train Accuracy: 0.2567, Val Loss: 1.6048, Val Accuracy: 0.2500 Epoch 356/10000, Train Loss: 1.6044, Train Accuracy: 0.2567, Val Loss: 1.6048, Val Accuracy: 0.2545 Epoch 357/10000, Train Loss: 1.6044, Train Accuracy: 0.2723, Val Loss: 1.6048, Val Accuracy: 0.2545 Epoch 358/10000, Train Loss: 1.6032, Train Accuracy: 0.2656, Val Loss: 1.6048, Val Accuracy: 0.2545 Epoch 359/10000, Train Loss: 1.6046, Train Accuracy: 0.2489, Val Loss: 1.6047, Val Accuracy: 0.2545 Epoch 360/10000, Train Loss: 1.6052, Train Accuracy: 0.2578, Val Loss: 1.6047, Val Accuracy: 0.2545 Epoch 361/10000, Train Loss: 1.6045, Train Accuracy: 0.2645, Val Loss: 1.6047, Val Accuracy: 0.2545 Epoch 362/10000, Train Loss: 1.6045, Train Accuracy: 0.2868, Val Loss: 1.6047, Val Accuracy: 0.2545 Epoch 363/10000, Train Loss: 1.6038, Train Accuracy: 0.2712, Val Loss: 1.6047, Val Accuracy: 0.2545 Epoch 364/10000, Train Loss: 1.6041, Train Accuracy: 0.2690, Val Loss: 1.6047, Val Accuracy: 0.2589 Epoch 365/10000, Train Loss: 1.6054, Train Accuracy: 0.2567, Val Loss: 1.6047, Val Accuracy: 0.2589 Epoch 366/10000, Train Loss: 1.6047, Train Accuracy: 0.2478, Val Loss: 1.6046, Val Accuracy: 0.2589 Epoch 367/10000, Train Loss: 1.6045, Train Accuracy: 0.2500, Val Loss: 1.6046, Val Accuracy: 0.2589 Epoch 368/10000, Train Loss: 1.6030, Train Accuracy: 0.2757, Val Loss: 1.6046, Val Accuracy: 0.2589 Epoch 369/10000, Train Loss: 1.6040, Train Accuracy: 0.2522, Val Loss: 1.6046, Val Accuracy: 0.2589 Epoch 370/10000, Train Loss: 1.6042, Train Accuracy: 0.2768, Val Loss: 1.6046, Val Accuracy: 0.2589 Epoch 371/10000, Train Loss: 1.6047, Train Accuracy: 0.2455, Val Loss: 1.6045, Val Accuracy: 0.2589 Epoch 372/10000, Train Loss: 1.6041, Train Accuracy: 0.2734, Val Loss: 1.6045, Val Accuracy: 0.2589 Epoch 373/10000, Train Loss: 1.6047, Train Accuracy: 0.2455, Val Loss: 1.6045, Val Accuracy: 0.2589 Epoch 374/10000, Train Loss: 1.6022, Train Accuracy: 0.2812, Val Loss: 1.6045, Val Accuracy: 0.2589 Epoch 375/10000, Train Loss: 1.6041, Train Accuracy: 0.2612, Val Loss: 1.6045, Val Accuracy: 0.2589 Epoch 376/10000, Train Loss: 1.6039, Train Accuracy: 0.2812, Val Loss: 1.6044, Val Accuracy: 0.2589 Epoch 377/10000, Train Loss: 1.6043, Train Accuracy: 0.2478, Val Loss: 1.6044, Val Accuracy: 0.2589 Epoch 378/10000, Train Loss: 1.6037, Train Accuracy: 0.2690, Val Loss: 1.6044, Val Accuracy: 0.2589 Epoch 379/10000, Train Loss: 1.6035, Train Accuracy: 0.2645, Val Loss: 1.6044, Val Accuracy: 0.2589 Epoch 380/10000, Train Loss: 1.6035, Train Accuracy: 0.2812, Val Loss: 1.6044, Val Accuracy: 0.2589 Epoch 381/10000, Train Loss: 1.6032, Train Accuracy: 0.2612, Val Loss: 1.6044, Val Accuracy: 0.2589 Epoch 382/10000, Train Loss: 1.6042, Train Accuracy: 0.2801, Val Loss: 1.6043, Val Accuracy: 0.2589 Epoch 383/10000, Train Loss: 1.6038, Train Accuracy: 0.2634, Val Loss: 1.6043, Val Accuracy: 0.2589 Epoch 384/10000, Train Loss: 1.6043, Train Accuracy: 0.2522, Val Loss: 1.6043, Val Accuracy: 0.2589 Epoch 385/10000, Train Loss: 1.6029, Train Accuracy: 0.2779, Val Loss: 1.6043, Val Accuracy: 0.2589 Epoch 386/10000, Train Loss: 1.6033, Train Accuracy: 0.2533, Val Loss: 1.6043, Val Accuracy: 0.2589 Epoch 387/10000, Train Loss: 1.6042, Train Accuracy: 0.2801, Val Loss: 1.6042, Val Accuracy: 0.2589 Epoch 388/10000, Train Loss: 1.6031, Train Accuracy: 0.2690, Val Loss: 1.6042, Val Accuracy: 0.2589 Epoch 389/10000, Train Loss: 1.6052, Train Accuracy: 0.2511, Val Loss: 1.6042, Val Accuracy: 0.2589 Epoch 390/10000, Train Loss: 1.6048, Train Accuracy: 0.2522, Val Loss: 1.6042, Val Accuracy: 0.2589 Epoch 391/10000, Train Loss: 1.6027, Train Accuracy: 0.2846, Val Loss: 1.6042, Val Accuracy: 0.2589 Epoch 392/10000, Train Loss: 1.6031, Train Accuracy: 0.2734, Val Loss: 1.6041, Val Accuracy: 0.2589 Epoch 393/10000, Train Loss: 1.6039, Train Accuracy: 0.2824, Val Loss: 1.6041, Val Accuracy: 0.2634 Epoch 394/10000, Train Loss: 1.6032, Train Accuracy: 0.2801, Val Loss: 1.6041, Val Accuracy: 0.2634 Epoch 395/10000, Train Loss: 1.6038, Train Accuracy: 0.2734, Val Loss: 1.6041, Val Accuracy: 0.2634 Epoch 396/10000, Train Loss: 1.6027, Train Accuracy: 0.2868, Val Loss: 1.6041, Val Accuracy: 0.2634 Epoch 397/10000, Train Loss: 1.6037, Train Accuracy: 0.2656, Val Loss: 1.6041, Val Accuracy: 0.2589 Epoch 398/10000, Train Loss: 1.6035, Train Accuracy: 0.2790, Val Loss: 1.6040, Val Accuracy: 0.2634 Epoch 399/10000, Train Loss: 1.6031, Train Accuracy: 0.2645, Val Loss: 1.6040, Val Accuracy: 0.2589 Epoch 400/10000, Train Loss: 1.6033, Train Accuracy: 0.2891, Val Loss: 1.6040, Val Accuracy: 0.2589 Epoch 401/10000, Train Loss: 1.6030, Train Accuracy: 0.2779, Val Loss: 1.6040, Val Accuracy: 0.2589 Epoch 402/10000, Train Loss: 1.6025, Train Accuracy: 0.2913, Val Loss: 1.6040, Val Accuracy: 0.2589 Epoch 403/10000, Train Loss: 1.6040, Train Accuracy: 0.2578, Val Loss: 1.6040, Val Accuracy: 0.2589 Epoch 404/10000, Train Loss: 1.6029, Train Accuracy: 0.2667, Val Loss: 1.6039, Val Accuracy: 0.2589 Epoch 405/10000, Train Loss: 1.6032, Train Accuracy: 0.2790, Val Loss: 1.6039, Val Accuracy: 0.2634 Epoch 406/10000, Train Loss: 1.6027, Train Accuracy: 0.2801, Val Loss: 1.6039, Val Accuracy: 0.2634 Epoch 407/10000, Train Loss: 1.6049, Train Accuracy: 0.2511, Val Loss: 1.6039, Val Accuracy: 0.2634 Epoch 408/10000, Train Loss: 1.6032, Train Accuracy: 0.2667, Val Loss: 1.6039, Val Accuracy: 0.2634 Epoch 409/10000, Train Loss: 1.6029, Train Accuracy: 0.2801, Val Loss: 1.6039, Val Accuracy: 0.2634 Epoch 410/10000, Train Loss: 1.6028, Train Accuracy: 0.2623, Val Loss: 1.6038, Val Accuracy: 0.2634 Epoch 411/10000, Train Loss: 1.6038, Train Accuracy: 0.2824, Val Loss: 1.6038, Val Accuracy: 0.2634 Epoch 412/10000, Train Loss: 1.6045, Train Accuracy: 0.2656, Val Loss: 1.6038, Val Accuracy: 0.2679 Epoch 413/10000, Train Loss: 1.6029, Train Accuracy: 0.2712, Val Loss: 1.6038, Val Accuracy: 0.2679 Epoch 414/10000, Train Loss: 1.6039, Train Accuracy: 0.2612, Val Loss: 1.6038, Val Accuracy: 0.2679 Epoch 415/10000, Train Loss: 1.6043, Train Accuracy: 0.2690, Val Loss: 1.6037, Val Accuracy: 0.2679 Epoch 416/10000, Train Loss: 1.6034, Train Accuracy: 0.2969, Val Loss: 1.6037, Val Accuracy: 0.2679 Epoch 417/10000, Train Loss: 1.6035, Train Accuracy: 0.2589, Val Loss: 1.6037, Val Accuracy: 0.2679 Epoch 418/10000, Train Loss: 1.6025, Train Accuracy: 0.2612, Val Loss: 1.6037, Val Accuracy: 0.2634 Epoch 419/10000, Train Loss: 1.6032, Train Accuracy: 0.2634, Val Loss: 1.6037, Val Accuracy: 0.2679 Epoch 420/10000, Train Loss: 1.6032, Train Accuracy: 0.2879, Val Loss: 1.6037, Val Accuracy: 0.2679 Epoch 421/10000, Train Loss: 1.6037, Train Accuracy: 0.2701, Val Loss: 1.6037, Val Accuracy: 0.2679 Epoch 422/10000, Train Loss: 1.6036, Train Accuracy: 0.2701, Val Loss: 1.6036, Val Accuracy: 0.2723 Epoch 423/10000, Train Loss: 1.6028, Train Accuracy: 0.2656, Val Loss: 1.6036, Val Accuracy: 0.2768 Epoch 424/10000, Train Loss: 1.6033, Train Accuracy: 0.2667, Val Loss: 1.6036, Val Accuracy: 0.2768 Epoch 425/10000, Train Loss: 1.6033, Train Accuracy: 0.2779, Val Loss: 1.6036, Val Accuracy: 0.2768 Epoch 426/10000, Train Loss: 1.6033, Train Accuracy: 0.2623, Val Loss: 1.6035, Val Accuracy: 0.2768 Epoch 427/10000, Train Loss: 1.6035, Train Accuracy: 0.2645, Val Loss: 1.6035, Val Accuracy: 0.2768 Epoch 428/10000, Train Loss: 1.6024, Train Accuracy: 0.2868, Val Loss: 1.6035, Val Accuracy: 0.2768 Epoch 429/10000, Train Loss: 1.6024, Train Accuracy: 0.2924, Val Loss: 1.6035, Val Accuracy: 0.2768 Epoch 430/10000, Train Loss: 1.6026, Train Accuracy: 0.2857, Val Loss: 1.6035, Val Accuracy: 0.2768 Epoch 431/10000, Train Loss: 1.6037, Train Accuracy: 0.2746, Val Loss: 1.6035, Val Accuracy: 0.2768 Epoch 432/10000, Train Loss: 1.6035, Train Accuracy: 0.2690, Val Loss: 1.6035, Val Accuracy: 0.2812 Epoch 433/10000, Train Loss: 1.6029, Train Accuracy: 0.2757, Val Loss: 1.6034, Val Accuracy: 0.2812 Epoch 434/10000, Train Loss: 1.6027, Train Accuracy: 0.2969, Val Loss: 1.6034, Val Accuracy: 0.2812 Epoch 435/10000, Train Loss: 1.6019, Train Accuracy: 0.2835, Val Loss: 1.6034, Val Accuracy: 0.2812 Epoch 436/10000, Train Loss: 1.6024, Train Accuracy: 0.2790, Val Loss: 1.6034, Val Accuracy: 0.2812 Epoch 437/10000, Train Loss: 1.6029, Train Accuracy: 0.2913, Val Loss: 1.6033, Val Accuracy: 0.2812 Epoch 438/10000, Train Loss: 1.6020, Train Accuracy: 0.2924, Val Loss: 1.6033, Val Accuracy: 0.2812 Epoch 439/10000, Train Loss: 1.6028, Train Accuracy: 0.2935, Val Loss: 1.6033, Val Accuracy: 0.2812 Epoch 440/10000, Train Loss: 1.6022, Train Accuracy: 0.2768, Val Loss: 1.6033, Val Accuracy: 0.2812 Epoch 441/10000, Train Loss: 1.6031, Train Accuracy: 0.2835, Val Loss: 1.6033, Val Accuracy: 0.2812 Epoch 442/10000, Train Loss: 1.6033, Train Accuracy: 0.2801, Val Loss: 1.6033, Val Accuracy: 0.2812 Epoch 443/10000, Train Loss: 1.6029, Train Accuracy: 0.2835, Val Loss: 1.6032, Val Accuracy: 0.2812 Epoch 444/10000, Train Loss: 1.6029, Train Accuracy: 0.2779, Val Loss: 1.6032, Val Accuracy: 0.2812 Epoch 445/10000, Train Loss: 1.6028, Train Accuracy: 0.2891, Val Loss: 1.6032, Val Accuracy: 0.2812 Epoch 446/10000, Train Loss: 1.6026, Train Accuracy: 0.2790, Val Loss: 1.6032, Val Accuracy: 0.2812 Epoch 447/10000, Train Loss: 1.6019, Train Accuracy: 0.2935, Val Loss: 1.6032, Val Accuracy: 0.2812 Epoch 448/10000, Train Loss: 1.6040, Train Accuracy: 0.2824, Val Loss: 1.6032, Val Accuracy: 0.2812 Epoch 449/10000, Train Loss: 1.6027, Train Accuracy: 0.2801, Val Loss: 1.6031, Val Accuracy: 0.2768 Epoch 450/10000, Train Loss: 1.6035, Train Accuracy: 0.2868, Val Loss: 1.6031, Val Accuracy: 0.2768 Epoch 451/10000, Train Loss: 1.6022, Train Accuracy: 0.2790, Val Loss: 1.6031, Val Accuracy: 0.2768 Epoch 452/10000, Train Loss: 1.6028, Train Accuracy: 0.2634, Val Loss: 1.6031, Val Accuracy: 0.2768 Epoch 453/10000, Train Loss: 1.6035, Train Accuracy: 0.2567, Val Loss: 1.6030, Val Accuracy: 0.2768 Epoch 454/10000, Train Loss: 1.6022, Train Accuracy: 0.2679, Val Loss: 1.6030, Val Accuracy: 0.2768 Epoch 455/10000, Train Loss: 1.6034, Train Accuracy: 0.2533, Val Loss: 1.6030, Val Accuracy: 0.2768 Epoch 456/10000, Train Loss: 1.6030, Train Accuracy: 0.2835, Val Loss: 1.6030, Val Accuracy: 0.2768 Epoch 457/10000, Train Loss: 1.6022, Train Accuracy: 0.2824, Val Loss: 1.6030, Val Accuracy: 0.2768 Epoch 458/10000, Train Loss: 1.6022, Train Accuracy: 0.2757, Val Loss: 1.6029, Val Accuracy: 0.2768 Epoch 459/10000, Train Loss: 1.6027, Train Accuracy: 0.2723, Val Loss: 1.6029, Val Accuracy: 0.2768 Epoch 460/10000, Train Loss: 1.6022, Train Accuracy: 0.2790, Val Loss: 1.6029, Val Accuracy: 0.2768 Epoch 461/10000, Train Loss: 1.6024, Train Accuracy: 0.2623, Val Loss: 1.6029, Val Accuracy: 0.2768 Epoch 462/10000, Train Loss: 1.6019, Train Accuracy: 0.2801, Val Loss: 1.6029, Val Accuracy: 0.2768 Epoch 463/10000, Train Loss: 1.6028, Train Accuracy: 0.2701, Val Loss: 1.6028, Val Accuracy: 0.2768 Epoch 464/10000, Train Loss: 1.6023, Train Accuracy: 0.2723, Val Loss: 1.6028, Val Accuracy: 0.2768 Epoch 465/10000, Train Loss: 1.6017, Train Accuracy: 0.2902, Val Loss: 1.6028, Val Accuracy: 0.2768 Epoch 466/10000, Train Loss: 1.6029, Train Accuracy: 0.2913, Val Loss: 1.6028, Val Accuracy: 0.2768 Epoch 467/10000, Train Loss: 1.6013, Train Accuracy: 0.2958, Val Loss: 1.6028, Val Accuracy: 0.2768 Epoch 468/10000, Train Loss: 1.6026, Train Accuracy: 0.2690, Val Loss: 1.6027, Val Accuracy: 0.2768 Epoch 469/10000, Train Loss: 1.6020, Train Accuracy: 0.2913, Val Loss: 1.6027, Val Accuracy: 0.2768 Epoch 470/10000, Train Loss: 1.6020, Train Accuracy: 0.2779, Val Loss: 1.6027, Val Accuracy: 0.2768 Epoch 471/10000, Train Loss: 1.6019, Train Accuracy: 0.2667, Val Loss: 1.6027, Val Accuracy: 0.2812 Epoch 472/10000, Train Loss: 1.6012, Train Accuracy: 0.2913, Val Loss: 1.6026, Val Accuracy: 0.2812 Epoch 473/10000, Train Loss: 1.6025, Train Accuracy: 0.2891, Val Loss: 1.6026, Val Accuracy: 0.2812 Epoch 474/10000, Train Loss: 1.6013, Train Accuracy: 0.2656, Val Loss: 1.6026, Val Accuracy: 0.2812 Epoch 475/10000, Train Loss: 1.6028, Train Accuracy: 0.2824, Val Loss: 1.6026, Val Accuracy: 0.2812 Epoch 476/10000, Train Loss: 1.6025, Train Accuracy: 0.2768, Val Loss: 1.6026, Val Accuracy: 0.2812 Epoch 477/10000, Train Loss: 1.5996, Train Accuracy: 0.3281, Val Loss: 1.6026, Val Accuracy: 0.2812 Epoch 478/10000, Train Loss: 1.6025, Train Accuracy: 0.2801, Val Loss: 1.6025, Val Accuracy: 0.2812 Epoch 479/10000, Train Loss: 1.6014, Train Accuracy: 0.3069, Val Loss: 1.6025, Val Accuracy: 0.2812 Epoch 480/10000, Train Loss: 1.6015, Train Accuracy: 0.2991, Val Loss: 1.6025, Val Accuracy: 0.2812 Epoch 481/10000, Train Loss: 1.6020, Train Accuracy: 0.2935, Val Loss: 1.6025, Val Accuracy: 0.2812 Epoch 482/10000, Train Loss: 1.6026, Train Accuracy: 0.2556, Val Loss: 1.6025, Val Accuracy: 0.2857 Epoch 483/10000, Train Loss: 1.6026, Train Accuracy: 0.2589, Val Loss: 1.6024, Val Accuracy: 0.2857 Epoch 484/10000, Train Loss: 1.6022, Train Accuracy: 0.2779, Val Loss: 1.6024, Val Accuracy: 0.2857 Epoch 485/10000, Train Loss: 1.6029, Train Accuracy: 0.2746, Val Loss: 1.6024, Val Accuracy: 0.2902 Epoch 486/10000, Train Loss: 1.6030, Train Accuracy: 0.2757, Val Loss: 1.6024, Val Accuracy: 0.2902 Epoch 487/10000, Train Loss: 1.6024, Train Accuracy: 0.2857, Val Loss: 1.6024, Val Accuracy: 0.2902 Epoch 488/10000, Train Loss: 1.6021, Train Accuracy: 0.2768, Val Loss: 1.6023, Val Accuracy: 0.2902 Epoch 489/10000, Train Loss: 1.6036, Train Accuracy: 0.2600, Val Loss: 1.6023, Val Accuracy: 0.2902 Epoch 490/10000, Train Loss: 1.6010, Train Accuracy: 0.2902, Val Loss: 1.6023, Val Accuracy: 0.2902 Epoch 491/10000, Train Loss: 1.6014, Train Accuracy: 0.2891, Val Loss: 1.6023, Val Accuracy: 0.2902 Epoch 492/10000, Train Loss: 1.6021, Train Accuracy: 0.2879, Val Loss: 1.6023, Val Accuracy: 0.2946 Epoch 493/10000, Train Loss: 1.6021, Train Accuracy: 0.2946, Val Loss: 1.6022, Val Accuracy: 0.2946 Epoch 494/10000, Train Loss: 1.6019, Train Accuracy: 0.2790, Val Loss: 1.6022, Val Accuracy: 0.2946 Epoch 495/10000, Train Loss: 1.6021, Train Accuracy: 0.2991, Val Loss: 1.6022, Val Accuracy: 0.2946 Epoch 496/10000, Train Loss: 1.6027, Train Accuracy: 0.2768, Val Loss: 1.6022, Val Accuracy: 0.2946 Epoch 497/10000, Train Loss: 1.6016, Train Accuracy: 0.2991, Val Loss: 1.6022, Val Accuracy: 0.2946 Epoch 498/10000, Train Loss: 1.6016, Train Accuracy: 0.2701, Val Loss: 1.6021, Val Accuracy: 0.2946 Epoch 499/10000, Train Loss: 1.6009, Train Accuracy: 0.3036, Val Loss: 1.6021, Val Accuracy: 0.2946 Epoch 500/10000, Train Loss: 1.6003, Train Accuracy: 0.2790, Val Loss: 1.6021, Val Accuracy: 0.2991 Epoch 501/10000, Train Loss: 1.6010, Train Accuracy: 0.2935, Val Loss: 1.6021, Val Accuracy: 0.2991 Epoch 502/10000, Train Loss: 1.6005, Train Accuracy: 0.2824, Val Loss: 1.6021, Val Accuracy: 0.2946 Epoch 503/10000, Train Loss: 1.6018, Train Accuracy: 0.2801, Val Loss: 1.6020, Val Accuracy: 0.2991 Epoch 504/10000, Train Loss: 1.6022, Train Accuracy: 0.2902, Val Loss: 1.6020, Val Accuracy: 0.2991 Epoch 505/10000, Train Loss: 1.6016, Train Accuracy: 0.3013, Val Loss: 1.6020, Val Accuracy: 0.2991 Epoch 506/10000, Train Loss: 1.6013, Train Accuracy: 0.3025, Val Loss: 1.6020, Val Accuracy: 0.2991 Epoch 507/10000, Train Loss: 1.6017, Train Accuracy: 0.2891, Val Loss: 1.6020, Val Accuracy: 0.2991 Epoch 508/10000, Train Loss: 1.6004, Train Accuracy: 0.3114, Val Loss: 1.6019, Val Accuracy: 0.2991 Epoch 509/10000, Train Loss: 1.6009, Train Accuracy: 0.2868, Val Loss: 1.6019, Val Accuracy: 0.2991 Epoch 510/10000, Train Loss: 1.6015, Train Accuracy: 0.2868, Val Loss: 1.6019, Val Accuracy: 0.2991
Epoch 511/10000, Train Loss: 1.6012, Train Accuracy: 0.2935, Val Loss: 1.6019, Val Accuracy: 0.2991 Epoch 512/10000, Train Loss: 1.6016, Train Accuracy: 0.2801, Val Loss: 1.6019, Val Accuracy: 0.2991 Epoch 513/10000, Train Loss: 1.6026, Train Accuracy: 0.2790, Val Loss: 1.6018, Val Accuracy: 0.2991 Epoch 514/10000, Train Loss: 1.6007, Train Accuracy: 0.2835, Val Loss: 1.6018, Val Accuracy: 0.2991 Epoch 515/10000, Train Loss: 1.6018, Train Accuracy: 0.2812, Val Loss: 1.6018, Val Accuracy: 0.2991 Epoch 516/10000, Train Loss: 1.6011, Train Accuracy: 0.2779, Val Loss: 1.6018, Val Accuracy: 0.2991 Epoch 517/10000, Train Loss: 1.6014, Train Accuracy: 0.2980, Val Loss: 1.6018, Val Accuracy: 0.2991 Epoch 518/10000, Train Loss: 1.6001, Train Accuracy: 0.3002, Val Loss: 1.6017, Val Accuracy: 0.2991 Epoch 519/10000, Train Loss: 1.6017, Train Accuracy: 0.2857, Val Loss: 1.6017, Val Accuracy: 0.2991 Epoch 520/10000, Train Loss: 1.6021, Train Accuracy: 0.2924, Val Loss: 1.6017, Val Accuracy: 0.2991 Epoch 521/10000, Train Loss: 1.6006, Train Accuracy: 0.3069, Val Loss: 1.6017, Val Accuracy: 0.2991 Epoch 522/10000, Train Loss: 1.6006, Train Accuracy: 0.3036, Val Loss: 1.6016, Val Accuracy: 0.2991 Epoch 523/10000, Train Loss: 1.6010, Train Accuracy: 0.2980, Val Loss: 1.6016, Val Accuracy: 0.2991 Epoch 524/10000, Train Loss: 1.6013, Train Accuracy: 0.2846, Val Loss: 1.6016, Val Accuracy: 0.2991 Epoch 525/10000, Train Loss: 1.6013, Train Accuracy: 0.2879, Val Loss: 1.6016, Val Accuracy: 0.2991 Epoch 526/10000, Train Loss: 1.6007, Train Accuracy: 0.3025, Val Loss: 1.6016, Val Accuracy: 0.2991 Epoch 527/10000, Train Loss: 1.6005, Train Accuracy: 0.3025, Val Loss: 1.6015, Val Accuracy: 0.2991 Epoch 528/10000, Train Loss: 1.6014, Train Accuracy: 0.3058, Val Loss: 1.6015, Val Accuracy: 0.2991 Epoch 529/10000, Train Loss: 1.6012, Train Accuracy: 0.2935, Val Loss: 1.6015, Val Accuracy: 0.2991 Epoch 530/10000, Train Loss: 1.5994, Train Accuracy: 0.3058, Val Loss: 1.6015, Val Accuracy: 0.2991 Epoch 531/10000, Train Loss: 1.6006, Train Accuracy: 0.3013, Val Loss: 1.6015, Val Accuracy: 0.2991 Epoch 532/10000, Train Loss: 1.5997, Train Accuracy: 0.2913, Val Loss: 1.6014, Val Accuracy: 0.2991 Epoch 533/10000, Train Loss: 1.6003, Train Accuracy: 0.3025, Val Loss: 1.6014, Val Accuracy: 0.2991 Epoch 534/10000, Train Loss: 1.6010, Train Accuracy: 0.2946, Val Loss: 1.6014, Val Accuracy: 0.2991 Epoch 535/10000, Train Loss: 1.6007, Train Accuracy: 0.2879, Val Loss: 1.6014, Val Accuracy: 0.3036 Epoch 536/10000, Train Loss: 1.6003, Train Accuracy: 0.2924, Val Loss: 1.6014, Val Accuracy: 0.3036 Epoch 537/10000, Train Loss: 1.6006, Train Accuracy: 0.2913, Val Loss: 1.6013, Val Accuracy: 0.3036 Epoch 538/10000, Train Loss: 1.6000, Train Accuracy: 0.3136, Val Loss: 1.6013, Val Accuracy: 0.3036 Epoch 539/10000, Train Loss: 1.6013, Train Accuracy: 0.2924, Val Loss: 1.6013, Val Accuracy: 0.3036 Epoch 540/10000, Train Loss: 1.5998, Train Accuracy: 0.3203, Val Loss: 1.6013, Val Accuracy: 0.3036 Epoch 541/10000, Train Loss: 1.6009, Train Accuracy: 0.3036, Val Loss: 1.6013, Val Accuracy: 0.3036 Epoch 542/10000, Train Loss: 1.5996, Train Accuracy: 0.3036, Val Loss: 1.6012, Val Accuracy: 0.3036 Epoch 543/10000, Train Loss: 1.5995, Train Accuracy: 0.2946, Val Loss: 1.6012, Val Accuracy: 0.3036 Epoch 544/10000, Train Loss: 1.5990, Train Accuracy: 0.3214, Val Loss: 1.6012, Val Accuracy: 0.3036 Epoch 545/10000, Train Loss: 1.6017, Train Accuracy: 0.2835, Val Loss: 1.6012, Val Accuracy: 0.3036 Epoch 546/10000, Train Loss: 1.6001, Train Accuracy: 0.3047, Val Loss: 1.6011, Val Accuracy: 0.2991 Epoch 547/10000, Train Loss: 1.5985, Train Accuracy: 0.3080, Val Loss: 1.6011, Val Accuracy: 0.3080 Epoch 548/10000, Train Loss: 1.6005, Train Accuracy: 0.3092, Val Loss: 1.6011, Val Accuracy: 0.3125 Epoch 549/10000, Train Loss: 1.6000, Train Accuracy: 0.2924, Val Loss: 1.6011, Val Accuracy: 0.3080 Epoch 550/10000, Train Loss: 1.6009, Train Accuracy: 0.2779, Val Loss: 1.6010, Val Accuracy: 0.3125 Epoch 551/10000, Train Loss: 1.6006, Train Accuracy: 0.3136, Val Loss: 1.6010, Val Accuracy: 0.3125 Epoch 552/10000, Train Loss: 1.6013, Train Accuracy: 0.2913, Val Loss: 1.6010, Val Accuracy: 0.3125 Epoch 553/10000, Train Loss: 1.6003, Train Accuracy: 0.2969, Val Loss: 1.6010, Val Accuracy: 0.3125 Epoch 554/10000, Train Loss: 1.6005, Train Accuracy: 0.3013, Val Loss: 1.6010, Val Accuracy: 0.3125 Epoch 555/10000, Train Loss: 1.6002, Train Accuracy: 0.3047, Val Loss: 1.6009, Val Accuracy: 0.3125 Epoch 556/10000, Train Loss: 1.5997, Train Accuracy: 0.3147, Val Loss: 1.6009, Val Accuracy: 0.3125 Epoch 557/10000, Train Loss: 1.5993, Train Accuracy: 0.3125, Val Loss: 1.6009, Val Accuracy: 0.3125 Epoch 558/10000, Train Loss: 1.6007, Train Accuracy: 0.2924, Val Loss: 1.6009, Val Accuracy: 0.3170 Epoch 559/10000, Train Loss: 1.6000, Train Accuracy: 0.2980, Val Loss: 1.6008, Val Accuracy: 0.3170 Epoch 560/10000, Train Loss: 1.6016, Train Accuracy: 0.2746, Val Loss: 1.6008, Val Accuracy: 0.3214 Epoch 561/10000, Train Loss: 1.6008, Train Accuracy: 0.2857, Val Loss: 1.6008, Val Accuracy: 0.3214 Epoch 562/10000, Train Loss: 1.5998, Train Accuracy: 0.3125, Val Loss: 1.6008, Val Accuracy: 0.3214 Epoch 563/10000, Train Loss: 1.6006, Train Accuracy: 0.2902, Val Loss: 1.6008, Val Accuracy: 0.3214 Epoch 564/10000, Train Loss: 1.6006, Train Accuracy: 0.2879, Val Loss: 1.6007, Val Accuracy: 0.3214 Epoch 565/10000, Train Loss: 1.6002, Train Accuracy: 0.3136, Val Loss: 1.6007, Val Accuracy: 0.3259 Epoch 566/10000, Train Loss: 1.5990, Train Accuracy: 0.3114, Val Loss: 1.6007, Val Accuracy: 0.3259 Epoch 567/10000, Train Loss: 1.6008, Train Accuracy: 0.2969, Val Loss: 1.6007, Val Accuracy: 0.3259 Epoch 568/10000, Train Loss: 1.5992, Train Accuracy: 0.3214, Val Loss: 1.6006, Val Accuracy: 0.3259 Epoch 569/10000, Train Loss: 1.6004, Train Accuracy: 0.2935, Val Loss: 1.6006, Val Accuracy: 0.3259 Epoch 570/10000, Train Loss: 1.5999, Train Accuracy: 0.3069, Val Loss: 1.6006, Val Accuracy: 0.3259 Epoch 571/10000, Train Loss: 1.5977, Train Accuracy: 0.3292, Val Loss: 1.6005, Val Accuracy: 0.3304 Epoch 572/10000, Train Loss: 1.5992, Train Accuracy: 0.3103, Val Loss: 1.6005, Val Accuracy: 0.3304 Epoch 573/10000, Train Loss: 1.5999, Train Accuracy: 0.2958, Val Loss: 1.6005, Val Accuracy: 0.3348 Epoch 574/10000, Train Loss: 1.5994, Train Accuracy: 0.2958, Val Loss: 1.6005, Val Accuracy: 0.3348 Epoch 575/10000, Train Loss: 1.5988, Train Accuracy: 0.3092, Val Loss: 1.6005, Val Accuracy: 0.3348 Epoch 576/10000, Train Loss: 1.5997, Train Accuracy: 0.2868, Val Loss: 1.6004, Val Accuracy: 0.3393 Epoch 577/10000, Train Loss: 1.5991, Train Accuracy: 0.2790, Val Loss: 1.6004, Val Accuracy: 0.3438 Epoch 578/10000, Train Loss: 1.5997, Train Accuracy: 0.3214, Val Loss: 1.6004, Val Accuracy: 0.3438 Epoch 579/10000, Train Loss: 1.5992, Train Accuracy: 0.3181, Val Loss: 1.6004, Val Accuracy: 0.3438 Epoch 580/10000, Train Loss: 1.6006, Train Accuracy: 0.3002, Val Loss: 1.6003, Val Accuracy: 0.3438 Epoch 581/10000, Train Loss: 1.5988, Train Accuracy: 0.3125, Val Loss: 1.6003, Val Accuracy: 0.3482 Epoch 582/10000, Train Loss: 1.5989, Train Accuracy: 0.2991, Val Loss: 1.6003, Val Accuracy: 0.3482 Epoch 583/10000, Train Loss: 1.6003, Train Accuracy: 0.2924, Val Loss: 1.6003, Val Accuracy: 0.3482 Epoch 584/10000, Train Loss: 1.5991, Train Accuracy: 0.2969, Val Loss: 1.6002, Val Accuracy: 0.3482 Epoch 585/10000, Train Loss: 1.5993, Train Accuracy: 0.3080, Val Loss: 1.6002, Val Accuracy: 0.3482 Epoch 586/10000, Train Loss: 1.5990, Train Accuracy: 0.3326, Val Loss: 1.6002, Val Accuracy: 0.3482 Epoch 587/10000, Train Loss: 1.6014, Train Accuracy: 0.2812, Val Loss: 1.6001, Val Accuracy: 0.3482 Epoch 588/10000, Train Loss: 1.6000, Train Accuracy: 0.3114, Val Loss: 1.6001, Val Accuracy: 0.3527 Epoch 589/10000, Train Loss: 1.6004, Train Accuracy: 0.2846, Val Loss: 1.6001, Val Accuracy: 0.3527 Epoch 590/10000, Train Loss: 1.5988, Train Accuracy: 0.3136, Val Loss: 1.6001, Val Accuracy: 0.3527 Epoch 591/10000, Train Loss: 1.6001, Train Accuracy: 0.3002, Val Loss: 1.6001, Val Accuracy: 0.3571 Epoch 592/10000, Train Loss: 1.5990, Train Accuracy: 0.3181, Val Loss: 1.6000, Val Accuracy: 0.3571 Epoch 593/10000, Train Loss: 1.5992, Train Accuracy: 0.3103, Val Loss: 1.6000, Val Accuracy: 0.3571 Epoch 594/10000, Train Loss: 1.6001, Train Accuracy: 0.3103, Val Loss: 1.6000, Val Accuracy: 0.3571 Epoch 595/10000, Train Loss: 1.5981, Train Accuracy: 0.3147, Val Loss: 1.6000, Val Accuracy: 0.3571 Epoch 596/10000, Train Loss: 1.5989, Train Accuracy: 0.3147, Val Loss: 1.5999, Val Accuracy: 0.3571 Epoch 597/10000, Train Loss: 1.5988, Train Accuracy: 0.2946, Val Loss: 1.5999, Val Accuracy: 0.3571 Epoch 598/10000, Train Loss: 1.5996, Train Accuracy: 0.3225, Val Loss: 1.5999, Val Accuracy: 0.3571 Epoch 599/10000, Train Loss: 1.5975, Train Accuracy: 0.3248, Val Loss: 1.5999, Val Accuracy: 0.3571 Epoch 600/10000, Train Loss: 1.5987, Train Accuracy: 0.3270, Val Loss: 1.5999, Val Accuracy: 0.3571 Epoch 601/10000, Train Loss: 1.5983, Train Accuracy: 0.3203, Val Loss: 1.5998, Val Accuracy: 0.3571 Epoch 602/10000, Train Loss: 1.5985, Train Accuracy: 0.3181, Val Loss: 1.5998, Val Accuracy: 0.3571 Epoch 603/10000, Train Loss: 1.5996, Train Accuracy: 0.3092, Val Loss: 1.5998, Val Accuracy: 0.3571 Epoch 604/10000, Train Loss: 1.5988, Train Accuracy: 0.3225, Val Loss: 1.5998, Val Accuracy: 0.3616 Epoch 605/10000, Train Loss: 1.5983, Train Accuracy: 0.3025, Val Loss: 1.5998, Val Accuracy: 0.3616 Epoch 606/10000, Train Loss: 1.5985, Train Accuracy: 0.2980, Val Loss: 1.5997, Val Accuracy: 0.3616 Epoch 607/10000, Train Loss: 1.5994, Train Accuracy: 0.3170, Val Loss: 1.5997, Val Accuracy: 0.3571 Epoch 608/10000, Train Loss: 1.5982, Train Accuracy: 0.3170, Val Loss: 1.5997, Val Accuracy: 0.3616 Epoch 609/10000, Train Loss: 1.5987, Train Accuracy: 0.2946, Val Loss: 1.5997, Val Accuracy: 0.3616 Epoch 610/10000, Train Loss: 1.5994, Train Accuracy: 0.3147, Val Loss: 1.5996, Val Accuracy: 0.3616 Epoch 611/10000, Train Loss: 1.5978, Train Accuracy: 0.3292, Val Loss: 1.5996, Val Accuracy: 0.3616 Epoch 612/10000, Train Loss: 1.5978, Train Accuracy: 0.3147, Val Loss: 1.5996, Val Accuracy: 0.3616 Epoch 613/10000, Train Loss: 1.5991, Train Accuracy: 0.3103, Val Loss: 1.5996, Val Accuracy: 0.3616 Epoch 614/10000, Train Loss: 1.5995, Train Accuracy: 0.2935, Val Loss: 1.5996, Val Accuracy: 0.3616 Epoch 615/10000, Train Loss: 1.5978, Train Accuracy: 0.3292, Val Loss: 1.5995, Val Accuracy: 0.3616 Epoch 616/10000, Train Loss: 1.5989, Train Accuracy: 0.3170, Val Loss: 1.5995, Val Accuracy: 0.3616 Epoch 617/10000, Train Loss: 1.5982, Train Accuracy: 0.3136, Val Loss: 1.5995, Val Accuracy: 0.3616 Epoch 618/10000, Train Loss: 1.5999, Train Accuracy: 0.3147, Val Loss: 1.5995, Val Accuracy: 0.3705 Epoch 619/10000, Train Loss: 1.5985, Train Accuracy: 0.3136, Val Loss: 1.5994, Val Accuracy: 0.3705 Epoch 620/10000, Train Loss: 1.5982, Train Accuracy: 0.2991, Val Loss: 1.5994, Val Accuracy: 0.3705 Epoch 621/10000, Train Loss: 1.5977, Train Accuracy: 0.3225, Val Loss: 1.5994, Val Accuracy: 0.3705 Epoch 622/10000, Train Loss: 1.5977, Train Accuracy: 0.3103, Val Loss: 1.5993, Val Accuracy: 0.3705 Epoch 623/10000, Train Loss: 1.5974, Train Accuracy: 0.3170, Val Loss: 1.5993, Val Accuracy: 0.3705 Epoch 624/10000, Train Loss: 1.5978, Train Accuracy: 0.3203, Val Loss: 1.5993, Val Accuracy: 0.3705 Epoch 625/10000, Train Loss: 1.5968, Train Accuracy: 0.3225, Val Loss: 1.5993, Val Accuracy: 0.3750 Epoch 626/10000, Train Loss: 1.5973, Train Accuracy: 0.3225, Val Loss: 1.5992, Val Accuracy: 0.3750 Epoch 627/10000, Train Loss: 1.5978, Train Accuracy: 0.3092, Val Loss: 1.5992, Val Accuracy: 0.3750 Epoch 628/10000, Train Loss: 1.5976, Train Accuracy: 0.3248, Val Loss: 1.5992, Val Accuracy: 0.3795 Epoch 629/10000, Train Loss: 1.5980, Train Accuracy: 0.3158, Val Loss: 1.5992, Val Accuracy: 0.3795 Epoch 630/10000, Train Loss: 1.5988, Train Accuracy: 0.3080, Val Loss: 1.5991, Val Accuracy: 0.3750 Epoch 631/10000, Train Loss: 1.5976, Train Accuracy: 0.3103, Val Loss: 1.5991, Val Accuracy: 0.3795 Epoch 632/10000, Train Loss: 1.5984, Train Accuracy: 0.2980, Val Loss: 1.5991, Val Accuracy: 0.3795 Epoch 633/10000, Train Loss: 1.5986, Train Accuracy: 0.2958, Val Loss: 1.5990, Val Accuracy: 0.3795 Epoch 634/10000, Train Loss: 1.5983, Train Accuracy: 0.3047, Val Loss: 1.5990, Val Accuracy: 0.3795 Epoch 635/10000, Train Loss: 1.5985, Train Accuracy: 0.3125, Val Loss: 1.5990, Val Accuracy: 0.3795 Epoch 636/10000, Train Loss: 1.5983, Train Accuracy: 0.3047, Val Loss: 1.5990, Val Accuracy: 0.3795 Epoch 637/10000, Train Loss: 1.5978, Train Accuracy: 0.3147, Val Loss: 1.5989, Val Accuracy: 0.3795 Epoch 638/10000, Train Loss: 1.5988, Train Accuracy: 0.3214, Val Loss: 1.5989, Val Accuracy: 0.3795 Epoch 639/10000, Train Loss: 1.5977, Train Accuracy: 0.3281, Val Loss: 1.5989, Val Accuracy: 0.3795 Epoch 640/10000, Train Loss: 1.5965, Train Accuracy: 0.3415, Val Loss: 1.5988, Val Accuracy: 0.3795 Epoch 641/10000, Train Loss: 1.5981, Train Accuracy: 0.3069, Val Loss: 1.5988, Val Accuracy: 0.3795 Epoch 642/10000, Train Loss: 1.5968, Train Accuracy: 0.3237, Val Loss: 1.5988, Val Accuracy: 0.3795 Epoch 643/10000, Train Loss: 1.5983, Train Accuracy: 0.3158, Val Loss: 1.5988, Val Accuracy: 0.3795 Epoch 644/10000, Train Loss: 1.5970, Train Accuracy: 0.3125, Val Loss: 1.5988, Val Accuracy: 0.3795 Epoch 645/10000, Train Loss: 1.5988, Train Accuracy: 0.2969, Val Loss: 1.5987, Val Accuracy: 0.3795 Epoch 646/10000, Train Loss: 1.6002, Train Accuracy: 0.3103, Val Loss: 1.5987, Val Accuracy: 0.3795 Epoch 647/10000, Train Loss: 1.5980, Train Accuracy: 0.3069, Val Loss: 1.5987, Val Accuracy: 0.3795 Epoch 648/10000, Train Loss: 1.5974, Train Accuracy: 0.3114, Val Loss: 1.5986, Val Accuracy: 0.3795 Epoch 649/10000, Train Loss: 1.5977, Train Accuracy: 0.3237, Val Loss: 1.5986, Val Accuracy: 0.3795 Epoch 650/10000, Train Loss: 1.5966, Train Accuracy: 0.3382, Val Loss: 1.5986, Val Accuracy: 0.3795 Epoch 651/10000, Train Loss: 1.5972, Train Accuracy: 0.3404, Val Loss: 1.5986, Val Accuracy: 0.3795 Epoch 652/10000, Train Loss: 1.5964, Train Accuracy: 0.3315, Val Loss: 1.5985, Val Accuracy: 0.3795 Epoch 653/10000, Train Loss: 1.5991, Train Accuracy: 0.2868, Val Loss: 1.5985, Val Accuracy: 0.3795 Epoch 654/10000, Train Loss: 1.5972, Train Accuracy: 0.3382, Val Loss: 1.5985, Val Accuracy: 0.3795 Epoch 655/10000, Train Loss: 1.5967, Train Accuracy: 0.3270, Val Loss: 1.5985, Val Accuracy: 0.3795 Epoch 656/10000, Train Loss: 1.5978, Train Accuracy: 0.3170, Val Loss: 1.5984, Val Accuracy: 0.3795 Epoch 657/10000, Train Loss: 1.5981, Train Accuracy: 0.3125, Val Loss: 1.5984, Val Accuracy: 0.3795 Epoch 658/10000, Train Loss: 1.5978, Train Accuracy: 0.3080, Val Loss: 1.5984, Val Accuracy: 0.3795 Epoch 659/10000, Train Loss: 1.5966, Train Accuracy: 0.3203, Val Loss: 1.5984, Val Accuracy: 0.3795 Epoch 660/10000, Train Loss: 1.5977, Train Accuracy: 0.3158, Val Loss: 1.5983, Val Accuracy: 0.3795 Epoch 661/10000, Train Loss: 1.5972, Train Accuracy: 0.3270, Val Loss: 1.5983, Val Accuracy: 0.3795 Epoch 662/10000, Train Loss: 1.5970, Train Accuracy: 0.3136, Val Loss: 1.5983, Val Accuracy: 0.3795 Epoch 663/10000, Train Loss: 1.5975, Train Accuracy: 0.3214, Val Loss: 1.5982, Val Accuracy: 0.3795 Epoch 664/10000, Train Loss: 1.5978, Train Accuracy: 0.3192, Val Loss: 1.5982, Val Accuracy: 0.3795 Epoch 665/10000, Train Loss: 1.5967, Train Accuracy: 0.3192, Val Loss: 1.5982, Val Accuracy: 0.3795 Epoch 666/10000, Train Loss: 1.5979, Train Accuracy: 0.3225, Val Loss: 1.5982, Val Accuracy: 0.3795 Epoch 667/10000, Train Loss: 1.5960, Train Accuracy: 0.3315, Val Loss: 1.5981, Val Accuracy: 0.3795 Epoch 668/10000, Train Loss: 1.5962, Train Accuracy: 0.3315, Val Loss: 1.5981, Val Accuracy: 0.3839 Epoch 669/10000, Train Loss: 1.5970, Train Accuracy: 0.3281, Val Loss: 1.5981, Val Accuracy: 0.3929 Epoch 670/10000, Train Loss: 1.5964, Train Accuracy: 0.3359, Val Loss: 1.5980, Val Accuracy: 0.3929 Epoch 671/10000, Train Loss: 1.5979, Train Accuracy: 0.3025, Val Loss: 1.5980, Val Accuracy: 0.3929 Epoch 672/10000, Train Loss: 1.5955, Train Accuracy: 0.3460, Val Loss: 1.5980, Val Accuracy: 0.3929 Epoch 673/10000, Train Loss: 1.5970, Train Accuracy: 0.3326, Val Loss: 1.5980, Val Accuracy: 0.3929 Epoch 674/10000, Train Loss: 1.5968, Train Accuracy: 0.3170, Val Loss: 1.5979, Val Accuracy: 0.3929 Epoch 675/10000, Train Loss: 1.5979, Train Accuracy: 0.3114, Val Loss: 1.5979, Val Accuracy: 0.3973 Epoch 676/10000, Train Loss: 1.5969, Train Accuracy: 0.3292, Val Loss: 1.5979, Val Accuracy: 0.3884 Epoch 677/10000, Train Loss: 1.5948, Train Accuracy: 0.3493, Val Loss: 1.5978, Val Accuracy: 0.3884 Epoch 678/10000, Train Loss: 1.5967, Train Accuracy: 0.3371, Val Loss: 1.5978, Val Accuracy: 0.3884 Epoch 679/10000, Train Loss: 1.5961, Train Accuracy: 0.3404, Val Loss: 1.5978, Val Accuracy: 0.3884 Epoch 680/10000, Train Loss: 1.5955, Train Accuracy: 0.3315, Val Loss: 1.5977, Val Accuracy: 0.3884 Epoch 681/10000, Train Loss: 1.5972, Train Accuracy: 0.3214, Val Loss: 1.5977, Val Accuracy: 0.3884 Epoch 682/10000, Train Loss: 1.5957, Train Accuracy: 0.3270, Val Loss: 1.5977, Val Accuracy: 0.3884 Epoch 683/10000, Train Loss: 1.5960, Train Accuracy: 0.3259, Val Loss: 1.5977, Val Accuracy: 0.3884 Epoch 684/10000, Train Loss: 1.5960, Train Accuracy: 0.3292, Val Loss: 1.5976, Val Accuracy: 0.3929 Epoch 685/10000, Train Loss: 1.5973, Train Accuracy: 0.3147, Val Loss: 1.5976, Val Accuracy: 0.3929 Epoch 686/10000, Train Loss: 1.5977, Train Accuracy: 0.3069, Val Loss: 1.5976, Val Accuracy: 0.3929 Epoch 687/10000, Train Loss: 1.5966, Train Accuracy: 0.3248, Val Loss: 1.5976, Val Accuracy: 0.3929 Epoch 688/10000, Train Loss: 1.5961, Train Accuracy: 0.3270, Val Loss: 1.5975, Val Accuracy: 0.3929 Epoch 689/10000, Train Loss: 1.5967, Train Accuracy: 0.3214, Val Loss: 1.5975, Val Accuracy: 0.3929 Epoch 690/10000, Train Loss: 1.5957, Train Accuracy: 0.3025, Val Loss: 1.5975, Val Accuracy: 0.3929 Epoch 691/10000, Train Loss: 1.5974, Train Accuracy: 0.3069, Val Loss: 1.5974, Val Accuracy: 0.3929 Epoch 692/10000, Train Loss: 1.5967, Train Accuracy: 0.3214, Val Loss: 1.5974, Val Accuracy: 0.3929 Epoch 693/10000, Train Loss: 1.5965, Train Accuracy: 0.3125, Val Loss: 1.5974, Val Accuracy: 0.3929 Epoch 694/10000, Train Loss: 1.5960, Train Accuracy: 0.3538, Val Loss: 1.5974, Val Accuracy: 0.3929 Epoch 695/10000, Train Loss: 1.5963, Train Accuracy: 0.3270, Val Loss: 1.5973, Val Accuracy: 0.3929 Epoch 696/10000, Train Loss: 1.5964, Train Accuracy: 0.3281, Val Loss: 1.5973, Val Accuracy: 0.3929 Epoch 697/10000, Train Loss: 1.5950, Train Accuracy: 0.3415, Val Loss: 1.5973, Val Accuracy: 0.3929 Epoch 698/10000, Train Loss: 1.5957, Train Accuracy: 0.3348, Val Loss: 1.5973, Val Accuracy: 0.3929 Epoch 699/10000, Train Loss: 1.5953, Train Accuracy: 0.3371, Val Loss: 1.5972, Val Accuracy: 0.3929 Epoch 700/10000, Train Loss: 1.5957, Train Accuracy: 0.3136, Val Loss: 1.5972, Val Accuracy: 0.3929 Epoch 701/10000, Train Loss: 1.5959, Train Accuracy: 0.3404, Val Loss: 1.5972, Val Accuracy: 0.3929 Epoch 702/10000, Train Loss: 1.5963, Train Accuracy: 0.3438, Val Loss: 1.5971, Val Accuracy: 0.3929 Epoch 703/10000, Train Loss: 1.5950, Train Accuracy: 0.3326, Val Loss: 1.5971, Val Accuracy: 0.3929 Epoch 704/10000, Train Loss: 1.5955, Train Accuracy: 0.3371, Val Loss: 1.5971, Val Accuracy: 0.3929 Epoch 705/10000, Train Loss: 1.5967, Train Accuracy: 0.3337, Val Loss: 1.5971, Val Accuracy: 0.3929 Epoch 706/10000, Train Loss: 1.5965, Train Accuracy: 0.3214, Val Loss: 1.5970, Val Accuracy: 0.3929 Epoch 707/10000, Train Loss: 1.5953, Train Accuracy: 0.3348, Val Loss: 1.5970, Val Accuracy: 0.3929 Epoch 708/10000, Train Loss: 1.5971, Train Accuracy: 0.3259, Val Loss: 1.5970, Val Accuracy: 0.3929 Epoch 709/10000, Train Loss: 1.5957, Train Accuracy: 0.3404, Val Loss: 1.5970, Val Accuracy: 0.3929 Epoch 710/10000, Train Loss: 1.5952, Train Accuracy: 0.3214, Val Loss: 1.5969, Val Accuracy: 0.3929 Epoch 711/10000, Train Loss: 1.5955, Train Accuracy: 0.3248, Val Loss: 1.5969, Val Accuracy: 0.3929 Epoch 712/10000, Train Loss: 1.5961, Train Accuracy: 0.3214, Val Loss: 1.5969, Val Accuracy: 0.3929 Epoch 713/10000, Train Loss: 1.5953, Train Accuracy: 0.3371, Val Loss: 1.5968, Val Accuracy: 0.3929 Epoch 714/10000, Train Loss: 1.5951, Train Accuracy: 0.3460, Val Loss: 1.5968, Val Accuracy: 0.3929 Epoch 715/10000, Train Loss: 1.5959, Train Accuracy: 0.3348, Val Loss: 1.5968, Val Accuracy: 0.3929 Epoch 716/10000, Train Loss: 1.5957, Train Accuracy: 0.3326, Val Loss: 1.5967, Val Accuracy: 0.3929 Epoch 717/10000, Train Loss: 1.5965, Train Accuracy: 0.3114, Val Loss: 1.5967, Val Accuracy: 0.3929 Epoch 718/10000, Train Loss: 1.5958, Train Accuracy: 0.3158, Val Loss: 1.5967, Val Accuracy: 0.3929 Epoch 719/10000, Train Loss: 1.5961, Train Accuracy: 0.3158, Val Loss: 1.5966, Val Accuracy: 0.3929 Epoch 720/10000, Train Loss: 1.5961, Train Accuracy: 0.3192, Val Loss: 1.5966, Val Accuracy: 0.3929 Epoch 721/10000, Train Loss: 1.5957, Train Accuracy: 0.3348, Val Loss: 1.5966, Val Accuracy: 0.3929 Epoch 722/10000, Train Loss: 1.5944, Train Accuracy: 0.3460, Val Loss: 1.5965, Val Accuracy: 0.3929 Epoch 723/10000, Train Loss: 1.5968, Train Accuracy: 0.3348, Val Loss: 1.5965, Val Accuracy: 0.3929 Epoch 724/10000, Train Loss: 1.5951, Train Accuracy: 0.3493, Val Loss: 1.5965, Val Accuracy: 0.3929 Epoch 725/10000, Train Loss: 1.5958, Train Accuracy: 0.3225, Val Loss: 1.5965, Val Accuracy: 0.3929 Epoch 726/10000, Train Loss: 1.5960, Train Accuracy: 0.2991, Val Loss: 1.5964, Val Accuracy: 0.3929 Epoch 727/10000, Train Loss: 1.5951, Train Accuracy: 0.3415, Val Loss: 1.5964, Val Accuracy: 0.3929 Epoch 728/10000, Train Loss: 1.5952, Train Accuracy: 0.3504, Val Loss: 1.5964, Val Accuracy: 0.3929 Epoch 729/10000, Train Loss: 1.5955, Train Accuracy: 0.3359, Val Loss: 1.5963, Val Accuracy: 0.3929 Epoch 730/10000, Train Loss: 1.5932, Train Accuracy: 0.3426, Val Loss: 1.5963, Val Accuracy: 0.3929 Epoch 731/10000, Train Loss: 1.5945, Train Accuracy: 0.3225, Val Loss: 1.5963, Val Accuracy: 0.3929 Epoch 732/10000, Train Loss: 1.5947, Train Accuracy: 0.3583, Val Loss: 1.5962, Val Accuracy: 0.3929 Epoch 733/10000, Train Loss: 1.5956, Train Accuracy: 0.3315, Val Loss: 1.5962, Val Accuracy: 0.3929 Epoch 734/10000, Train Loss: 1.5941, Train Accuracy: 0.3337, Val Loss: 1.5962, Val Accuracy: 0.3929 Epoch 735/10000, Train Loss: 1.5954, Train Accuracy: 0.3259, Val Loss: 1.5961, Val Accuracy: 0.3929 Epoch 736/10000, Train Loss: 1.5967, Train Accuracy: 0.3092, Val Loss: 1.5961, Val Accuracy: 0.3929 Epoch 737/10000, Train Loss: 1.5952, Train Accuracy: 0.3259, Val Loss: 1.5961, Val Accuracy: 0.3929 Epoch 738/10000, Train Loss: 1.5957, Train Accuracy: 0.3147, Val Loss: 1.5961, Val Accuracy: 0.3929 Epoch 739/10000, Train Loss: 1.5953, Train Accuracy: 0.3371, Val Loss: 1.5961, Val Accuracy: 0.3929 Epoch 740/10000, Train Loss: 1.5935, Train Accuracy: 0.3426, Val Loss: 1.5960, Val Accuracy: 0.3929 Epoch 741/10000, Train Loss: 1.5949, Train Accuracy: 0.3516, Val Loss: 1.5960, Val Accuracy: 0.3929 Epoch 742/10000, Train Loss: 1.5964, Train Accuracy: 0.3237, Val Loss: 1.5960, Val Accuracy: 0.3929 Epoch 743/10000, Train Loss: 1.5952, Train Accuracy: 0.3337, Val Loss: 1.5959, Val Accuracy: 0.3929 Epoch 744/10000, Train Loss: 1.5941, Train Accuracy: 0.3415, Val Loss: 1.5959, Val Accuracy: 0.3929 Epoch 745/10000, Train Loss: 1.5941, Train Accuracy: 0.3493, Val Loss: 1.5959, Val Accuracy: 0.3929 Epoch 746/10000, Train Loss: 1.5957, Train Accuracy: 0.3270, Val Loss: 1.5959, Val Accuracy: 0.3929 Epoch 747/10000, Train Loss: 1.5941, Train Accuracy: 0.3438, Val Loss: 1.5958, Val Accuracy: 0.3929 Epoch 748/10000, Train Loss: 1.5954, Train Accuracy: 0.3426, Val Loss: 1.5958, Val Accuracy: 0.3929 Epoch 749/10000, Train Loss: 1.5934, Train Accuracy: 0.3393, Val Loss: 1.5957, Val Accuracy: 0.3929 Epoch 750/10000, Train Loss: 1.5933, Train Accuracy: 0.3482, Val Loss: 1.5957, Val Accuracy: 0.3929 Epoch 751/10000, Train Loss: 1.5949, Train Accuracy: 0.3348, Val Loss: 1.5957, Val Accuracy: 0.3929 Epoch 752/10000, Train Loss: 1.5944, Train Accuracy: 0.3270, Val Loss: 1.5956, Val Accuracy: 0.3929 Epoch 753/10000, Train Loss: 1.5942, Train Accuracy: 0.3337, Val Loss: 1.5956, Val Accuracy: 0.3929 Epoch 754/10000, Train Loss: 1.5945, Train Accuracy: 0.3237, Val Loss: 1.5956, Val Accuracy: 0.3929 Epoch 755/10000, Train Loss: 1.5951, Train Accuracy: 0.3337, Val Loss: 1.5955, Val Accuracy: 0.3929 Epoch 756/10000, Train Loss: 1.5934, Train Accuracy: 0.3449, Val Loss: 1.5955, Val Accuracy: 0.3929 Epoch 757/10000, Train Loss: 1.5931, Train Accuracy: 0.3426, Val Loss: 1.5954, Val Accuracy: 0.3929 Epoch 758/10000, Train Loss: 1.5955, Train Accuracy: 0.3225, Val Loss: 1.5954, Val Accuracy: 0.3929 Epoch 759/10000, Train Loss: 1.5929, Train Accuracy: 0.3359, Val Loss: 1.5954, Val Accuracy: 0.3929 Epoch 760/10000, Train Loss: 1.5928, Train Accuracy: 0.3359, Val Loss: 1.5953, Val Accuracy: 0.3929 Epoch 761/10000, Train Loss: 1.5940, Train Accuracy: 0.3638, Val Loss: 1.5953, Val Accuracy: 0.3929 Epoch 762/10000, Train Loss: 1.5934, Train Accuracy: 0.3281, Val Loss: 1.5953, Val Accuracy: 0.3884 Epoch 763/10000, Train Loss: 1.5940, Train Accuracy: 0.3415, Val Loss: 1.5953, Val Accuracy: 0.3929 Epoch 764/10000, Train Loss: 1.5942, Train Accuracy: 0.3292, Val Loss: 1.5952, Val Accuracy: 0.3929 Epoch 765/10000, Train Loss: 1.5940, Train Accuracy: 0.3460, Val Loss: 1.5952, Val Accuracy: 0.3884 Epoch 766/10000, Train Loss: 1.5944, Train Accuracy: 0.3248, Val Loss: 1.5952, Val Accuracy: 0.3884 Epoch 767/10000, Train Loss: 1.5920, Train Accuracy: 0.3504, Val Loss: 1.5951, Val Accuracy: 0.3884 Epoch 768/10000, Train Loss: 1.5929, Train Accuracy: 0.3449, Val Loss: 1.5951, Val Accuracy: 0.3884 Epoch 769/10000, Train Loss: 1.5929, Train Accuracy: 0.3683, Val Loss: 1.5951, Val Accuracy: 0.3884 Epoch 770/10000, Train Loss: 1.5941, Train Accuracy: 0.3348, Val Loss: 1.5950, Val Accuracy: 0.3884 Epoch 771/10000, Train Loss: 1.5922, Train Accuracy: 0.3627, Val Loss: 1.5950, Val Accuracy: 0.3884 Epoch 772/10000, Train Loss: 1.5918, Train Accuracy: 0.3516, Val Loss: 1.5950, Val Accuracy: 0.3884 Epoch 773/10000, Train Loss: 1.5930, Train Accuracy: 0.3237, Val Loss: 1.5949, Val Accuracy: 0.3884 Epoch 774/10000, Train Loss: 1.5944, Train Accuracy: 0.3125, Val Loss: 1.5949, Val Accuracy: 0.3839 Epoch 775/10000, Train Loss: 1.5932, Train Accuracy: 0.3516, Val Loss: 1.5949, Val Accuracy: 0.3884 Epoch 776/10000, Train Loss: 1.5922, Train Accuracy: 0.3404, Val Loss: 1.5948, Val Accuracy: 0.3884 Epoch 777/10000, Train Loss: 1.5928, Train Accuracy: 0.3348, Val Loss: 1.5948, Val Accuracy: 0.3884 Epoch 778/10000, Train Loss: 1.5935, Train Accuracy: 0.3359, Val Loss: 1.5947, Val Accuracy: 0.3884 Epoch 779/10000, Train Loss: 1.5932, Train Accuracy: 0.3404, Val Loss: 1.5947, Val Accuracy: 0.3884 Epoch 780/10000, Train Loss: 1.5925, Train Accuracy: 0.3583, Val Loss: 1.5947, Val Accuracy: 0.3929 Epoch 781/10000, Train Loss: 1.5931, Train Accuracy: 0.3281, Val Loss: 1.5946, Val Accuracy: 0.3884 Epoch 782/10000, Train Loss: 1.5937, Train Accuracy: 0.3348, Val Loss: 1.5946, Val Accuracy: 0.3884 Epoch 783/10000, Train Loss: 1.5935, Train Accuracy: 0.3382, Val Loss: 1.5946, Val Accuracy: 0.3884 Epoch 784/10000, Train Loss: 1.5918, Train Accuracy: 0.3516, Val Loss: 1.5946, Val Accuracy: 0.3839 Epoch 785/10000, Train Loss: 1.5927, Train Accuracy: 0.3393, Val Loss: 1.5945, Val Accuracy: 0.3839 Epoch 786/10000, Train Loss: 1.5932, Train Accuracy: 0.3192, Val Loss: 1.5945, Val Accuracy: 0.3839 Epoch 787/10000, Train Loss: 1.5918, Train Accuracy: 0.3605, Val Loss: 1.5945, Val Accuracy: 0.3839 Epoch 788/10000, Train Loss: 1.5934, Train Accuracy: 0.3304, Val Loss: 1.5944, Val Accuracy: 0.3884 Epoch 789/10000, Train Loss: 1.5938, Train Accuracy: 0.3315, Val Loss: 1.5944, Val Accuracy: 0.3884 Epoch 790/10000, Train Loss: 1.5917, Train Accuracy: 0.3594, Val Loss: 1.5944, Val Accuracy: 0.3884 Epoch 791/10000, Train Loss: 1.5935, Train Accuracy: 0.3382, Val Loss: 1.5943, Val Accuracy: 0.3884 Epoch 792/10000, Train Loss: 1.5927, Train Accuracy: 0.3348, Val Loss: 1.5943, Val Accuracy: 0.3929 Epoch 793/10000, Train Loss: 1.5924, Train Accuracy: 0.3348, Val Loss: 1.5942, Val Accuracy: 0.3929 Epoch 794/10000, Train Loss: 1.5940, Train Accuracy: 0.3225, Val Loss: 1.5942, Val Accuracy: 0.3929 Epoch 795/10000, Train Loss: 1.5923, Train Accuracy: 0.3192, Val Loss: 1.5941, Val Accuracy: 0.3929 Epoch 796/10000, Train Loss: 1.5916, Train Accuracy: 0.3549, Val Loss: 1.5941, Val Accuracy: 0.3929 Epoch 797/10000, Train Loss: 1.5918, Train Accuracy: 0.3694, Val Loss: 1.5940, Val Accuracy: 0.3973 Epoch 798/10000, Train Loss: 1.5937, Train Accuracy: 0.3315, Val Loss: 1.5940, Val Accuracy: 0.3973 Epoch 799/10000, Train Loss: 1.5934, Train Accuracy: 0.3393, Val Loss: 1.5940, Val Accuracy: 0.3973 Epoch 800/10000, Train Loss: 1.5920, Train Accuracy: 0.3404, Val Loss: 1.5939, Val Accuracy: 0.3973 Epoch 801/10000, Train Loss: 1.5926, Train Accuracy: 0.3438, Val Loss: 1.5939, Val Accuracy: 0.3973 Epoch 802/10000, Train Loss: 1.5929, Train Accuracy: 0.3426, Val Loss: 1.5939, Val Accuracy: 0.3973 Epoch 803/10000, Train Loss: 1.5923, Train Accuracy: 0.3348, Val Loss: 1.5939, Val Accuracy: 0.3973 Epoch 804/10000, Train Loss: 1.5925, Train Accuracy: 0.3449, Val Loss: 1.5938, Val Accuracy: 0.3973 Epoch 805/10000, Train Loss: 1.5929, Train Accuracy: 0.3438, Val Loss: 1.5938, Val Accuracy: 0.3973 Epoch 806/10000, Train Loss: 1.5916, Train Accuracy: 0.3482, Val Loss: 1.5937, Val Accuracy: 0.3929 Epoch 807/10000, Train Loss: 1.5925, Train Accuracy: 0.3426, Val Loss: 1.5937, Val Accuracy: 0.3929 Epoch 808/10000, Train Loss: 1.5915, Train Accuracy: 0.3449, Val Loss: 1.5937, Val Accuracy: 0.3929 Epoch 809/10000, Train Loss: 1.5927, Train Accuracy: 0.3449, Val Loss: 1.5936, Val Accuracy: 0.3929 Epoch 810/10000, Train Loss: 1.5911, Train Accuracy: 0.3482, Val Loss: 1.5936, Val Accuracy: 0.4018 Epoch 811/10000, Train Loss: 1.5917, Train Accuracy: 0.3549, Val Loss: 1.5936, Val Accuracy: 0.3929 Epoch 812/10000, Train Loss: 1.5933, Train Accuracy: 0.3449, Val Loss: 1.5935, Val Accuracy: 0.3973 Epoch 813/10000, Train Loss: 1.5913, Train Accuracy: 0.3650, Val Loss: 1.5935, Val Accuracy: 0.3973 Epoch 814/10000, Train Loss: 1.5913, Train Accuracy: 0.3504, Val Loss: 1.5934, Val Accuracy: 0.3973 Epoch 815/10000, Train Loss: 1.5918, Train Accuracy: 0.3404, Val Loss: 1.5934, Val Accuracy: 0.3973 Epoch 816/10000, Train Loss: 1.5911, Train Accuracy: 0.3393, Val Loss: 1.5934, Val Accuracy: 0.3973 Epoch 817/10000, Train Loss: 1.5928, Train Accuracy: 0.3348, Val Loss: 1.5933, Val Accuracy: 0.3973 Epoch 818/10000, Train Loss: 1.5921, Train Accuracy: 0.3348, Val Loss: 1.5933, Val Accuracy: 0.3973 Epoch 819/10000, Train Loss: 1.5909, Train Accuracy: 0.3571, Val Loss: 1.5933, Val Accuracy: 0.3973 Epoch 820/10000, Train Loss: 1.5915, Train Accuracy: 0.3404, Val Loss: 1.5932, Val Accuracy: 0.3973 Epoch 821/10000, Train Loss: 1.5932, Train Accuracy: 0.3225, Val Loss: 1.5932, Val Accuracy: 0.3973 Epoch 822/10000, Train Loss: 1.5918, Train Accuracy: 0.3348, Val Loss: 1.5931, Val Accuracy: 0.3973 Epoch 823/10000, Train Loss: 1.5912, Train Accuracy: 0.3371, Val Loss: 1.5931, Val Accuracy: 0.4018 Epoch 824/10000, Train Loss: 1.5909, Train Accuracy: 0.3471, Val Loss: 1.5931, Val Accuracy: 0.4018 Epoch 825/10000, Train Loss: 1.5911, Train Accuracy: 0.3438, Val Loss: 1.5930, Val Accuracy: 0.4018 Epoch 826/10000, Train Loss: 1.5927, Train Accuracy: 0.3560, Val Loss: 1.5930, Val Accuracy: 0.4018 Epoch 827/10000, Train Loss: 1.5902, Train Accuracy: 0.3616, Val Loss: 1.5930, Val Accuracy: 0.3973 Epoch 828/10000, Train Loss: 1.5908, Train Accuracy: 0.3571, Val Loss: 1.5929, Val Accuracy: 0.3973 Epoch 829/10000, Train Loss: 1.5917, Train Accuracy: 0.3382, Val Loss: 1.5929, Val Accuracy: 0.3929 Epoch 830/10000, Train Loss: 1.5900, Train Accuracy: 0.3583, Val Loss: 1.5929, Val Accuracy: 0.3973 Epoch 831/10000, Train Loss: 1.5909, Train Accuracy: 0.3504, Val Loss: 1.5928, Val Accuracy: 0.3929 Epoch 832/10000, Train Loss: 1.5900, Train Accuracy: 0.3683, Val Loss: 1.5928, Val Accuracy: 0.3929 Epoch 833/10000, Train Loss: 1.5908, Train Accuracy: 0.3493, Val Loss: 1.5928, Val Accuracy: 0.3929 Epoch 834/10000, Train Loss: 1.5911, Train Accuracy: 0.3527, Val Loss: 1.5927, Val Accuracy: 0.3929 Epoch 835/10000, Train Loss: 1.5908, Train Accuracy: 0.3304, Val Loss: 1.5927, Val Accuracy: 0.3929 Epoch 836/10000, Train Loss: 1.5897, Train Accuracy: 0.3493, Val Loss: 1.5926, Val Accuracy: 0.3929 Epoch 837/10000, Train Loss: 1.5901, Train Accuracy: 0.3493, Val Loss: 1.5926, Val Accuracy: 0.3929 Epoch 838/10000, Train Loss: 1.5892, Train Accuracy: 0.3638, Val Loss: 1.5926, Val Accuracy: 0.3929 Epoch 839/10000, Train Loss: 1.5908, Train Accuracy: 0.3504, Val Loss: 1.5925, Val Accuracy: 0.3929 Epoch 840/10000, Train Loss: 1.5912, Train Accuracy: 0.3650, Val Loss: 1.5925, Val Accuracy: 0.3929 Epoch 841/10000, Train Loss: 1.5905, Train Accuracy: 0.3471, Val Loss: 1.5924, Val Accuracy: 0.3929 Epoch 842/10000, Train Loss: 1.5906, Train Accuracy: 0.3460, Val Loss: 1.5924, Val Accuracy: 0.3929 Epoch 843/10000, Train Loss: 1.5899, Train Accuracy: 0.3571, Val Loss: 1.5923, Val Accuracy: 0.3929 Epoch 844/10000, Train Loss: 1.5910, Train Accuracy: 0.3438, Val Loss: 1.5923, Val Accuracy: 0.3929 Epoch 845/10000, Train Loss: 1.5918, Train Accuracy: 0.3292, Val Loss: 1.5922, Val Accuracy: 0.3929 Epoch 846/10000, Train Loss: 1.5920, Train Accuracy: 0.3382, Val Loss: 1.5922, Val Accuracy: 0.3929 Epoch 847/10000, Train Loss: 1.5907, Train Accuracy: 0.3415, Val Loss: 1.5922, Val Accuracy: 0.3929 Epoch 848/10000, Train Loss: 1.5909, Train Accuracy: 0.3404, Val Loss: 1.5921, Val Accuracy: 0.3929 Epoch 849/10000, Train Loss: 1.5897, Train Accuracy: 0.3650, Val Loss: 1.5921, Val Accuracy: 0.3929 Epoch 850/10000, Train Loss: 1.5904, Train Accuracy: 0.3348, Val Loss: 1.5920, Val Accuracy: 0.3929 Epoch 851/10000, Train Loss: 1.5899, Train Accuracy: 0.3516, Val Loss: 1.5920, Val Accuracy: 0.3929 Epoch 852/10000, Train Loss: 1.5899, Train Accuracy: 0.3527, Val Loss: 1.5920, Val Accuracy: 0.3929 Epoch 853/10000, Train Loss: 1.5906, Train Accuracy: 0.3549, Val Loss: 1.5919, Val Accuracy: 0.3884 Epoch 854/10000, Train Loss: 1.5894, Train Accuracy: 0.3560, Val Loss: 1.5919, Val Accuracy: 0.3929 Epoch 855/10000, Train Loss: 1.5893, Train Accuracy: 0.3538, Val Loss: 1.5918, Val Accuracy: 0.3929 Epoch 856/10000, Train Loss: 1.5908, Train Accuracy: 0.3627, Val Loss: 1.5918, Val Accuracy: 0.3973 Epoch 857/10000, Train Loss: 1.5898, Train Accuracy: 0.3683, Val Loss: 1.5918, Val Accuracy: 0.3973 Epoch 858/10000, Train Loss: 1.5896, Train Accuracy: 0.3772, Val Loss: 1.5917, Val Accuracy: 0.3973 Epoch 859/10000, Train Loss: 1.5911, Train Accuracy: 0.3404, Val Loss: 1.5917, Val Accuracy: 0.3973 Epoch 860/10000, Train Loss: 1.5906, Train Accuracy: 0.3415, Val Loss: 1.5916, Val Accuracy: 0.3973 Epoch 861/10000, Train Loss: 1.5908, Train Accuracy: 0.3371, Val Loss: 1.5916, Val Accuracy: 0.3973 Epoch 862/10000, Train Loss: 1.5912, Train Accuracy: 0.3404, Val Loss: 1.5916, Val Accuracy: 0.3973 Epoch 863/10000, Train Loss: 1.5898, Train Accuracy: 0.3482, Val Loss: 1.5915, Val Accuracy: 0.3973 Epoch 864/10000, Train Loss: 1.5888, Train Accuracy: 0.3538, Val Loss: 1.5915, Val Accuracy: 0.3973 Epoch 865/10000, Train Loss: 1.5898, Train Accuracy: 0.3605, Val Loss: 1.5915, Val Accuracy: 0.3973 Epoch 866/10000, Train Loss: 1.5905, Train Accuracy: 0.3315, Val Loss: 1.5914, Val Accuracy: 0.3973 Epoch 867/10000, Train Loss: 1.5904, Train Accuracy: 0.3449, Val Loss: 1.5914, Val Accuracy: 0.3973 Epoch 868/10000, Train Loss: 1.5901, Train Accuracy: 0.3449, Val Loss: 1.5913, Val Accuracy: 0.3973 Epoch 869/10000, Train Loss: 1.5887, Train Accuracy: 0.3471, Val Loss: 1.5913, Val Accuracy: 0.3973 Epoch 870/10000, Train Loss: 1.5876, Train Accuracy: 0.3705, Val Loss: 1.5912, Val Accuracy: 0.3973 Epoch 871/10000, Train Loss: 1.5896, Train Accuracy: 0.3404, Val Loss: 1.5912, Val Accuracy: 0.3973 Epoch 872/10000, Train Loss: 1.5901, Train Accuracy: 0.3382, Val Loss: 1.5911, Val Accuracy: 0.4018 Epoch 873/10000, Train Loss: 1.5907, Train Accuracy: 0.3237, Val Loss: 1.5911, Val Accuracy: 0.4018 Epoch 874/10000, Train Loss: 1.5876, Train Accuracy: 0.3594, Val Loss: 1.5911, Val Accuracy: 0.4018 Epoch 875/10000, Train Loss: 1.5890, Train Accuracy: 0.3359, Val Loss: 1.5910, Val Accuracy: 0.4018 Epoch 876/10000, Train Loss: 1.5905, Train Accuracy: 0.3516, Val Loss: 1.5910, Val Accuracy: 0.4018 Epoch 877/10000, Train Loss: 1.5879, Train Accuracy: 0.3661, Val Loss: 1.5909, Val Accuracy: 0.4018 Epoch 878/10000, Train Loss: 1.5898, Train Accuracy: 0.3504, Val Loss: 1.5909, Val Accuracy: 0.4018 Epoch 879/10000, Train Loss: 1.5886, Train Accuracy: 0.3583, Val Loss: 1.5908, Val Accuracy: 0.4018 Epoch 880/10000, Train Loss: 1.5898, Train Accuracy: 0.3482, Val Loss: 1.5908, Val Accuracy: 0.4018 Epoch 881/10000, Train Loss: 1.5894, Train Accuracy: 0.3560, Val Loss: 1.5907, Val Accuracy: 0.4062 Epoch 882/10000, Train Loss: 1.5900, Train Accuracy: 0.3449, Val Loss: 1.5906, Val Accuracy: 0.4062 Epoch 883/10000, Train Loss: 1.5876, Train Accuracy: 0.3761, Val Loss: 1.5906, Val Accuracy: 0.4062 Epoch 884/10000, Train Loss: 1.5894, Train Accuracy: 0.3538, Val Loss: 1.5906, Val Accuracy: 0.4062 Epoch 885/10000, Train Loss: 1.5894, Train Accuracy: 0.3315, Val Loss: 1.5906, Val Accuracy: 0.4062 Epoch 886/10000, Train Loss: 1.5899, Train Accuracy: 0.3638, Val Loss: 1.5905, Val Accuracy: 0.4062 Epoch 887/10000, Train Loss: 1.5878, Train Accuracy: 0.3583, Val Loss: 1.5905, Val Accuracy: 0.4062 Epoch 888/10000, Train Loss: 1.5871, Train Accuracy: 0.3705, Val Loss: 1.5904, Val Accuracy: 0.4062 Epoch 889/10000, Train Loss: 1.5879, Train Accuracy: 0.3739, Val Loss: 1.5904, Val Accuracy: 0.4062 Epoch 890/10000, Train Loss: 1.5879, Train Accuracy: 0.3627, Val Loss: 1.5903, Val Accuracy: 0.4062 Epoch 891/10000, Train Loss: 1.5877, Train Accuracy: 0.3538, Val Loss: 1.5903, Val Accuracy: 0.4062 Epoch 892/10000, Train Loss: 1.5883, Train Accuracy: 0.3571, Val Loss: 1.5902, Val Accuracy: 0.4062 Epoch 893/10000, Train Loss: 1.5874, Train Accuracy: 0.3549, Val Loss: 1.5902, Val Accuracy: 0.4062 Epoch 894/10000, Train Loss: 1.5895, Train Accuracy: 0.3371, Val Loss: 1.5901, Val Accuracy: 0.4107 Epoch 895/10000, Train Loss: 1.5877, Train Accuracy: 0.3594, Val Loss: 1.5901, Val Accuracy: 0.4107 Epoch 896/10000, Train Loss: 1.5883, Train Accuracy: 0.3426, Val Loss: 1.5900, Val Accuracy: 0.4107 Epoch 897/10000, Train Loss: 1.5892, Train Accuracy: 0.3493, Val Loss: 1.5900, Val Accuracy: 0.4107 Epoch 898/10000, Train Loss: 1.5887, Train Accuracy: 0.3549, Val Loss: 1.5899, Val Accuracy: 0.4107 Epoch 899/10000, Train Loss: 1.5868, Train Accuracy: 0.3650, Val Loss: 1.5899, Val Accuracy: 0.4107 Epoch 900/10000, Train Loss: 1.5875, Train Accuracy: 0.3504, Val Loss: 1.5898, Val Accuracy: 0.4107 Epoch 901/10000, Train Loss: 1.5877, Train Accuracy: 0.3460, Val Loss: 1.5898, Val Accuracy: 0.4107 Epoch 902/10000, Train Loss: 1.5884, Train Accuracy: 0.3605, Val Loss: 1.5898, Val Accuracy: 0.4107 Epoch 903/10000, Train Loss: 1.5875, Train Accuracy: 0.3594, Val Loss: 1.5897, Val Accuracy: 0.4107 Epoch 904/10000, Train Loss: 1.5893, Train Accuracy: 0.3650, Val Loss: 1.5897, Val Accuracy: 0.4107 Epoch 905/10000, Train Loss: 1.5865, Train Accuracy: 0.3616, Val Loss: 1.5896, Val Accuracy: 0.4062 Epoch 906/10000, Train Loss: 1.5876, Train Accuracy: 0.3806, Val Loss: 1.5896, Val Accuracy: 0.4062 Epoch 907/10000, Train Loss: 1.5859, Train Accuracy: 0.3772, Val Loss: 1.5895, Val Accuracy: 0.4062 Epoch 908/10000, Train Loss: 1.5879, Train Accuracy: 0.3672, Val Loss: 1.5895, Val Accuracy: 0.4062 Epoch 909/10000, Train Loss: 1.5865, Train Accuracy: 0.3694, Val Loss: 1.5894, Val Accuracy: 0.4062 Epoch 910/10000, Train Loss: 1.5884, Train Accuracy: 0.3538, Val Loss: 1.5894, Val Accuracy: 0.4062 Epoch 911/10000, Train Loss: 1.5890, Train Accuracy: 0.3404, Val Loss: 1.5893, Val Accuracy: 0.4062 Epoch 912/10000, Train Loss: 1.5875, Train Accuracy: 0.3661, Val Loss: 1.5893, Val Accuracy: 0.4062 Epoch 913/10000, Train Loss: 1.5895, Train Accuracy: 0.3315, Val Loss: 1.5892, Val Accuracy: 0.4062 Epoch 914/10000, Train Loss: 1.5872, Train Accuracy: 0.3638, Val Loss: 1.5892, Val Accuracy: 0.4062 Epoch 915/10000, Train Loss: 1.5872, Train Accuracy: 0.3460, Val Loss: 1.5892, Val Accuracy: 0.4062 Epoch 916/10000, Train Loss: 1.5877, Train Accuracy: 0.3460, Val Loss: 1.5891, Val Accuracy: 0.4062 Epoch 917/10000, Train Loss: 1.5875, Train Accuracy: 0.3516, Val Loss: 1.5891, Val Accuracy: 0.4062 Epoch 918/10000, Train Loss: 1.5870, Train Accuracy: 0.3560, Val Loss: 1.5890, Val Accuracy: 0.4062 Epoch 919/10000, Train Loss: 1.5867, Train Accuracy: 0.3460, Val Loss: 1.5890, Val Accuracy: 0.4062 Epoch 920/10000, Train Loss: 1.5870, Train Accuracy: 0.3527, Val Loss: 1.5889, Val Accuracy: 0.4107 Epoch 921/10000, Train Loss: 1.5870, Train Accuracy: 0.3605, Val Loss: 1.5889, Val Accuracy: 0.4062 Epoch 922/10000, Train Loss: 1.5873, Train Accuracy: 0.3571, Val Loss: 1.5888, Val Accuracy: 0.4062 Epoch 923/10000, Train Loss: 1.5875, Train Accuracy: 0.3594, Val Loss: 1.5887, Val Accuracy: 0.4062 Epoch 924/10000, Train Loss: 1.5878, Train Accuracy: 0.3460, Val Loss: 1.5887, Val Accuracy: 0.4062 Epoch 925/10000, Train Loss: 1.5870, Train Accuracy: 0.3438, Val Loss: 1.5886, Val Accuracy: 0.4062 Epoch 926/10000, Train Loss: 1.5858, Train Accuracy: 0.3538, Val Loss: 1.5886, Val Accuracy: 0.4062 Epoch 927/10000, Train Loss: 1.5875, Train Accuracy: 0.3560, Val Loss: 1.5886, Val Accuracy: 0.4062 Epoch 928/10000, Train Loss: 1.5862, Train Accuracy: 0.3449, Val Loss: 1.5885, Val Accuracy: 0.4062 Epoch 929/10000, Train Loss: 1.5861, Train Accuracy: 0.3661, Val Loss: 1.5885, Val Accuracy: 0.4062 Epoch 930/10000, Train Loss: 1.5863, Train Accuracy: 0.3571, Val Loss: 1.5884, Val Accuracy: 0.4062 Epoch 931/10000, Train Loss: 1.5873, Train Accuracy: 0.3650, Val Loss: 1.5884, Val Accuracy: 0.4062 Epoch 932/10000, Train Loss: 1.5872, Train Accuracy: 0.3371, Val Loss: 1.5883, Val Accuracy: 0.4062 Epoch 933/10000, Train Loss: 1.5867, Train Accuracy: 0.3504, Val Loss: 1.5882, Val Accuracy: 0.4062 Epoch 934/10000, Train Loss: 1.5865, Train Accuracy: 0.3571, Val Loss: 1.5882, Val Accuracy: 0.4062 Epoch 935/10000, Train Loss: 1.5854, Train Accuracy: 0.3683, Val Loss: 1.5881, Val Accuracy: 0.4062 Epoch 936/10000, Train Loss: 1.5860, Train Accuracy: 0.3627, Val Loss: 1.5881, Val Accuracy: 0.4062 Epoch 937/10000, Train Loss: 1.5852, Train Accuracy: 0.3605, Val Loss: 1.5880, Val Accuracy: 0.4062 Epoch 938/10000, Train Loss: 1.5853, Train Accuracy: 0.3694, Val Loss: 1.5880, Val Accuracy: 0.4062 Epoch 939/10000, Train Loss: 1.5871, Train Accuracy: 0.3694, Val Loss: 1.5879, Val Accuracy: 0.4018 Epoch 940/10000, Train Loss: 1.5854, Train Accuracy: 0.3616, Val Loss: 1.5879, Val Accuracy: 0.4018 Epoch 941/10000, Train Loss: 1.5864, Train Accuracy: 0.3538, Val Loss: 1.5878, Val Accuracy: 0.4062 Epoch 942/10000, Train Loss: 1.5872, Train Accuracy: 0.3739, Val Loss: 1.5878, Val Accuracy: 0.4062 Epoch 943/10000, Train Loss: 1.5855, Train Accuracy: 0.3538, Val Loss: 1.5877, Val Accuracy: 0.4062 Epoch 944/10000, Train Loss: 1.5848, Train Accuracy: 0.3906, Val Loss: 1.5877, Val Accuracy: 0.4062 Epoch 945/10000, Train Loss: 1.5854, Train Accuracy: 0.3761, Val Loss: 1.5876, Val Accuracy: 0.4062 Epoch 946/10000, Train Loss: 1.5854, Train Accuracy: 0.3571, Val Loss: 1.5876, Val Accuracy: 0.4062 Epoch 947/10000, Train Loss: 1.5858, Train Accuracy: 0.3594, Val Loss: 1.5875, Val Accuracy: 0.4062 Epoch 948/10000, Train Loss: 1.5847, Train Accuracy: 0.3482, Val Loss: 1.5875, Val Accuracy: 0.4018 Epoch 949/10000, Train Loss: 1.5855, Train Accuracy: 0.3348, Val Loss: 1.5874, Val Accuracy: 0.4018 Epoch 950/10000, Train Loss: 1.5856, Train Accuracy: 0.3739, Val Loss: 1.5874, Val Accuracy: 0.3973 Epoch 951/10000, Train Loss: 1.5864, Train Accuracy: 0.3705, Val Loss: 1.5873, Val Accuracy: 0.3973 Epoch 952/10000, Train Loss: 1.5859, Train Accuracy: 0.3549, Val Loss: 1.5872, Val Accuracy: 0.3973 Epoch 953/10000, Train Loss: 1.5847, Train Accuracy: 0.3694, Val Loss: 1.5872, Val Accuracy: 0.3973 Epoch 954/10000, Train Loss: 1.5843, Train Accuracy: 0.3828, Val Loss: 1.5871, Val Accuracy: 0.3973 Epoch 955/10000, Train Loss: 1.5849, Train Accuracy: 0.3627, Val Loss: 1.5871, Val Accuracy: 0.3973 Epoch 956/10000, Train Loss: 1.5848, Train Accuracy: 0.3594, Val Loss: 1.5870, Val Accuracy: 0.3973 Epoch 957/10000, Train Loss: 1.5848, Train Accuracy: 0.3638, Val Loss: 1.5870, Val Accuracy: 0.3973 Epoch 958/10000, Train Loss: 1.5869, Train Accuracy: 0.3471, Val Loss: 1.5869, Val Accuracy: 0.3973 Epoch 959/10000, Train Loss: 1.5857, Train Accuracy: 0.3393, Val Loss: 1.5869, Val Accuracy: 0.3973 Epoch 960/10000, Train Loss: 1.5829, Train Accuracy: 0.3750, Val Loss: 1.5868, Val Accuracy: 0.3973 Epoch 961/10000, Train Loss: 1.5849, Train Accuracy: 0.3627, Val Loss: 1.5868, Val Accuracy: 0.3973 Epoch 962/10000, Train Loss: 1.5854, Train Accuracy: 0.3382, Val Loss: 1.5867, Val Accuracy: 0.3973 Epoch 963/10000, Train Loss: 1.5846, Train Accuracy: 0.3538, Val Loss: 1.5867, Val Accuracy: 0.3973 Epoch 964/10000, Train Loss: 1.5839, Train Accuracy: 0.3583, Val Loss: 1.5866, Val Accuracy: 0.3973 Epoch 965/10000, Train Loss: 1.5843, Train Accuracy: 0.3638, Val Loss: 1.5865, Val Accuracy: 0.3973 Epoch 966/10000, Train Loss: 1.5865, Train Accuracy: 0.3337, Val Loss: 1.5865, Val Accuracy: 0.3973 Epoch 967/10000, Train Loss: 1.5860, Train Accuracy: 0.3549, Val Loss: 1.5864, Val Accuracy: 0.3973 Epoch 968/10000, Train Loss: 1.5852, Train Accuracy: 0.3594, Val Loss: 1.5864, Val Accuracy: 0.3973 Epoch 969/10000, Train Loss: 1.5855, Train Accuracy: 0.3549, Val Loss: 1.5863, Val Accuracy: 0.3973 Epoch 970/10000, Train Loss: 1.5854, Train Accuracy: 0.3638, Val Loss: 1.5862, Val Accuracy: 0.3973 Epoch 971/10000, Train Loss: 1.5847, Train Accuracy: 0.3426, Val Loss: 1.5862, Val Accuracy: 0.3973 Epoch 972/10000, Train Loss: 1.5834, Train Accuracy: 0.3627, Val Loss: 1.5862, Val Accuracy: 0.3973 Epoch 973/10000, Train Loss: 1.5847, Train Accuracy: 0.3571, Val Loss: 1.5861, Val Accuracy: 0.3973 Epoch 974/10000, Train Loss: 1.5840, Train Accuracy: 0.3571, Val Loss: 1.5861, Val Accuracy: 0.3973 Epoch 975/10000, Train Loss: 1.5845, Train Accuracy: 0.3594, Val Loss: 1.5860, Val Accuracy: 0.3973 Epoch 976/10000, Train Loss: 1.5834, Train Accuracy: 0.3560, Val Loss: 1.5859, Val Accuracy: 0.3973 Epoch 977/10000, Train Loss: 1.5834, Train Accuracy: 0.3605, Val Loss: 1.5859, Val Accuracy: 0.3973 Epoch 978/10000, Train Loss: 1.5825, Train Accuracy: 0.3850, Val Loss: 1.5858, Val Accuracy: 0.3973 Epoch 979/10000, Train Loss: 1.5836, Train Accuracy: 0.3661, Val Loss: 1.5858, Val Accuracy: 0.3973 Epoch 980/10000, Train Loss: 1.5829, Train Accuracy: 0.3750, Val Loss: 1.5857, Val Accuracy: 0.3973 Epoch 981/10000, Train Loss: 1.5827, Train Accuracy: 0.3694, Val Loss: 1.5857, Val Accuracy: 0.3973 Epoch 982/10000, Train Loss: 1.5847, Train Accuracy: 0.3527, Val Loss: 1.5856, Val Accuracy: 0.3973 Epoch 983/10000, Train Loss: 1.5850, Train Accuracy: 0.3650, Val Loss: 1.5856, Val Accuracy: 0.3973 Epoch 984/10000, Train Loss: 1.5836, Train Accuracy: 0.3728, Val Loss: 1.5855, Val Accuracy: 0.3973 Epoch 985/10000, Train Loss: 1.5839, Train Accuracy: 0.3616, Val Loss: 1.5854, Val Accuracy: 0.3973 Epoch 986/10000, Train Loss: 1.5816, Train Accuracy: 0.3750, Val Loss: 1.5854, Val Accuracy: 0.3973 Epoch 987/10000, Train Loss: 1.5820, Train Accuracy: 0.3493, Val Loss: 1.5853, Val Accuracy: 0.3973 Epoch 988/10000, Train Loss: 1.5832, Train Accuracy: 0.3683, Val Loss: 1.5853, Val Accuracy: 0.3973 Epoch 989/10000, Train Loss: 1.5814, Train Accuracy: 0.3717, Val Loss: 1.5852, Val Accuracy: 0.3929 Epoch 990/10000, Train Loss: 1.5847, Train Accuracy: 0.3605, Val Loss: 1.5851, Val Accuracy: 0.3929 Epoch 991/10000, Train Loss: 1.5820, Train Accuracy: 0.3616, Val Loss: 1.5850, Val Accuracy: 0.3929 Epoch 992/10000, Train Loss: 1.5831, Train Accuracy: 0.3661, Val Loss: 1.5850, Val Accuracy: 0.3929 Epoch 993/10000, Train Loss: 1.5837, Train Accuracy: 0.3616, Val Loss: 1.5849, Val Accuracy: 0.3929 Epoch 994/10000, Train Loss: 1.5836, Train Accuracy: 0.3638, Val Loss: 1.5848, Val Accuracy: 0.3884 Epoch 995/10000, Train Loss: 1.5831, Train Accuracy: 0.3638, Val Loss: 1.5848, Val Accuracy: 0.3884 Epoch 996/10000, Train Loss: 1.5836, Train Accuracy: 0.3549, Val Loss: 1.5847, Val Accuracy: 0.3884 Epoch 997/10000, Train Loss: 1.5831, Train Accuracy: 0.3348, Val Loss: 1.5847, Val Accuracy: 0.3884 Epoch 998/10000, Train Loss: 1.5827, Train Accuracy: 0.3717, Val Loss: 1.5846, Val Accuracy: 0.3884 Epoch 999/10000, Train Loss: 1.5839, Train Accuracy: 0.3705, Val Loss: 1.5846, Val Accuracy: 0.3884 Epoch 1000/10000, Train Loss: 1.5850, Train Accuracy: 0.3527, Val Loss: 1.5845, Val Accuracy: 0.3884 Epoch 1001/10000, Train Loss: 1.5826, Train Accuracy: 0.3672, Val Loss: 1.5844, Val Accuracy: 0.3884 Epoch 1002/10000, Train Loss: 1.5813, Train Accuracy: 0.3694, Val Loss: 1.5844, Val Accuracy: 0.3884 Epoch 1003/10000, Train Loss: 1.5820, Train Accuracy: 0.3728, Val Loss: 1.5843, Val Accuracy: 0.3884 Epoch 1004/10000, Train Loss: 1.5827, Train Accuracy: 0.3795, Val Loss: 1.5842, Val Accuracy: 0.3884 Epoch 1005/10000, Train Loss: 1.5789, Train Accuracy: 0.3862, Val Loss: 1.5842, Val Accuracy: 0.3884 Epoch 1006/10000, Train Loss: 1.5812, Train Accuracy: 0.3873, Val Loss: 1.5841, Val Accuracy: 0.3884 Epoch 1007/10000, Train Loss: 1.5819, Train Accuracy: 0.3728, Val Loss: 1.5840, Val Accuracy: 0.3884 Epoch 1008/10000, Train Loss: 1.5821, Train Accuracy: 0.3527, Val Loss: 1.5840, Val Accuracy: 0.3884 Epoch 1009/10000, Train Loss: 1.5835, Train Accuracy: 0.3616, Val Loss: 1.5839, Val Accuracy: 0.3884 Epoch 1010/10000, Train Loss: 1.5802, Train Accuracy: 0.3616, Val Loss: 1.5839, Val Accuracy: 0.3884 Epoch 1011/10000, Train Loss: 1.5829, Train Accuracy: 0.3739, Val Loss: 1.5838, Val Accuracy: 0.3884 Epoch 1012/10000, Train Loss: 1.5811, Train Accuracy: 0.3638, Val Loss: 1.5837, Val Accuracy: 0.3884 Epoch 1013/10000, Train Loss: 1.5822, Train Accuracy: 0.3650, Val Loss: 1.5837, Val Accuracy: 0.3884 Epoch 1014/10000, Train Loss: 1.5800, Train Accuracy: 0.3873, Val Loss: 1.5836, Val Accuracy: 0.3884 Epoch 1015/10000, Train Loss: 1.5816, Train Accuracy: 0.3996, Val Loss: 1.5836, Val Accuracy: 0.3884 Epoch 1016/10000, Train Loss: 1.5846, Train Accuracy: 0.3571, Val Loss: 1.5835, Val Accuracy: 0.3884 Epoch 1017/10000, Train Loss: 1.5822, Train Accuracy: 0.3650, Val Loss: 1.5834, Val Accuracy: 0.3884 Epoch 1018/10000, Train Loss: 1.5782, Train Accuracy: 0.3940, Val Loss: 1.5833, Val Accuracy: 0.3884 Epoch 1019/10000, Train Loss: 1.5820, Train Accuracy: 0.3493, Val Loss: 1.5832, Val Accuracy: 0.3884 Epoch 1020/10000, Train Loss: 1.5811, Train Accuracy: 0.3850, Val Loss: 1.5832, Val Accuracy: 0.3884 Epoch 1021/10000, Train Loss: 1.5828, Train Accuracy: 0.3583, Val Loss: 1.5831, Val Accuracy: 0.3884 Epoch 1022/10000, Train Loss: 1.5792, Train Accuracy: 0.3873, Val Loss: 1.5831, Val Accuracy: 0.3884 Epoch 1023/10000, Train Loss: 1.5823, Train Accuracy: 0.3571, Val Loss: 1.5830, Val Accuracy: 0.3884 Epoch 1024/10000, Train Loss: 1.5815, Train Accuracy: 0.3739, Val Loss: 1.5829, Val Accuracy: 0.3884 Epoch 1025/10000, Train Loss: 1.5809, Train Accuracy: 0.3761, Val Loss: 1.5829, Val Accuracy: 0.3884 Epoch 1026/10000, Train Loss: 1.5818, Train Accuracy: 0.3672, Val Loss: 1.5828, Val Accuracy: 0.3884 Epoch 1027/10000, Train Loss: 1.5802, Train Accuracy: 0.3627, Val Loss: 1.5828, Val Accuracy: 0.3884 Epoch 1028/10000, Train Loss: 1.5808, Train Accuracy: 0.3683, Val Loss: 1.5827, Val Accuracy: 0.3884 Epoch 1029/10000, Train Loss: 1.5795, Train Accuracy: 0.3940, Val Loss: 1.5826, Val Accuracy: 0.3884 Epoch 1030/10000, Train Loss: 1.5804, Train Accuracy: 0.3527, Val Loss: 1.5826, Val Accuracy: 0.3884 Epoch 1031/10000, Train Loss: 1.5803, Train Accuracy: 0.3817, Val Loss: 1.5825, Val Accuracy: 0.3884 Epoch 1032/10000, Train Loss: 1.5782, Train Accuracy: 0.3828, Val Loss: 1.5825, Val Accuracy: 0.3884 Epoch 1033/10000, Train Loss: 1.5789, Train Accuracy: 0.3661, Val Loss: 1.5824, Val Accuracy: 0.3884 Epoch 1034/10000, Train Loss: 1.5792, Train Accuracy: 0.3750, Val Loss: 1.5823, Val Accuracy: 0.3884 Epoch 1035/10000, Train Loss: 1.5813, Train Accuracy: 0.3516, Val Loss: 1.5822, Val Accuracy: 0.3884 Epoch 1036/10000, Train Loss: 1.5797, Train Accuracy: 0.3705, Val Loss: 1.5822, Val Accuracy: 0.3884 Epoch 1037/10000, Train Loss: 1.5813, Train Accuracy: 0.3683, Val Loss: 1.5821, Val Accuracy: 0.3884 Epoch 1038/10000, Train Loss: 1.5789, Train Accuracy: 0.3705, Val Loss: 1.5820, Val Accuracy: 0.3884 Epoch 1039/10000, Train Loss: 1.5807, Train Accuracy: 0.3638, Val Loss: 1.5820, Val Accuracy: 0.3884 Epoch 1040/10000, Train Loss: 1.5801, Train Accuracy: 0.3627, Val Loss: 1.5819, Val Accuracy: 0.3884 Epoch 1041/10000, Train Loss: 1.5813, Train Accuracy: 0.3661, Val Loss: 1.5818, Val Accuracy: 0.3929 Epoch 1042/10000, Train Loss: 1.5798, Train Accuracy: 0.3571, Val Loss: 1.5817, Val Accuracy: 0.3929 Epoch 1043/10000, Train Loss: 1.5806, Train Accuracy: 0.3605, Val Loss: 1.5817, Val Accuracy: 0.3929 Epoch 1044/10000, Train Loss: 1.5746, Train Accuracy: 0.4085, Val Loss: 1.5816, Val Accuracy: 0.3929 Epoch 1045/10000, Train Loss: 1.5795, Train Accuracy: 0.3828, Val Loss: 1.5815, Val Accuracy: 0.3973 Epoch 1046/10000, Train Loss: 1.5770, Train Accuracy: 0.3917, Val Loss: 1.5815, Val Accuracy: 0.3973 Epoch 1047/10000, Train Loss: 1.5790, Train Accuracy: 0.3795, Val Loss: 1.5814, Val Accuracy: 0.3973 Epoch 1048/10000, Train Loss: 1.5787, Train Accuracy: 0.3739, Val Loss: 1.5813, Val Accuracy: 0.3973 Epoch 1049/10000, Train Loss: 1.5799, Train Accuracy: 0.3650, Val Loss: 1.5813, Val Accuracy: 0.3973 Epoch 1050/10000, Train Loss: 1.5775, Train Accuracy: 0.3828, Val Loss: 1.5812, Val Accuracy: 0.3973 Epoch 1051/10000, Train Loss: 1.5787, Train Accuracy: 0.3761, Val Loss: 1.5811, Val Accuracy: 0.3973 Epoch 1052/10000, Train Loss: 1.5782, Train Accuracy: 0.3650, Val Loss: 1.5810, Val Accuracy: 0.3973 Epoch 1053/10000, Train Loss: 1.5773, Train Accuracy: 0.3783, Val Loss: 1.5810, Val Accuracy: 0.3973 Epoch 1054/10000, Train Loss: 1.5826, Train Accuracy: 0.3393, Val Loss: 1.5808, Val Accuracy: 0.3973 Epoch 1055/10000, Train Loss: 1.5783, Train Accuracy: 0.3538, Val Loss: 1.5808, Val Accuracy: 0.3973 Epoch 1056/10000, Train Loss: 1.5791, Train Accuracy: 0.3717, Val Loss: 1.5807, Val Accuracy: 0.3973 Epoch 1057/10000, Train Loss: 1.5767, Train Accuracy: 0.3783, Val Loss: 1.5806, Val Accuracy: 0.3973 Epoch 1058/10000, Train Loss: 1.5778, Train Accuracy: 0.3895, Val Loss: 1.5806, Val Accuracy: 0.3973 Epoch 1059/10000, Train Loss: 1.5788, Train Accuracy: 0.3795, Val Loss: 1.5805, Val Accuracy: 0.3973 Epoch 1060/10000, Train Loss: 1.5792, Train Accuracy: 0.3438, Val Loss: 1.5805, Val Accuracy: 0.3973 Epoch 1061/10000, Train Loss: 1.5778, Train Accuracy: 0.3616, Val Loss: 1.5804, Val Accuracy: 0.3973 Epoch 1062/10000, Train Loss: 1.5792, Train Accuracy: 0.3627, Val Loss: 1.5803, Val Accuracy: 0.3973 Epoch 1063/10000, Train Loss: 1.5805, Train Accuracy: 0.3493, Val Loss: 1.5802, Val Accuracy: 0.3973 Epoch 1064/10000, Train Loss: 1.5787, Train Accuracy: 0.3415, Val Loss: 1.5801, Val Accuracy: 0.3973 Epoch 1065/10000, Train Loss: 1.5773, Train Accuracy: 0.3772, Val Loss: 1.5801, Val Accuracy: 0.3973 Epoch 1066/10000, Train Loss: 1.5781, Train Accuracy: 0.3783, Val Loss: 1.5800, Val Accuracy: 0.3973 Epoch 1067/10000, Train Loss: 1.5783, Train Accuracy: 0.3560, Val Loss: 1.5799, Val Accuracy: 0.3973 Epoch 1068/10000, Train Loss: 1.5773, Train Accuracy: 0.3750, Val Loss: 1.5798, Val Accuracy: 0.3973 Epoch 1069/10000, Train Loss: 1.5788, Train Accuracy: 0.3705, Val Loss: 1.5798, Val Accuracy: 0.3973 Epoch 1070/10000, Train Loss: 1.5776, Train Accuracy: 0.3627, Val Loss: 1.5797, Val Accuracy: 0.3973 Epoch 1071/10000, Train Loss: 1.5786, Train Accuracy: 0.3828, Val Loss: 1.5796, Val Accuracy: 0.4018 Epoch 1072/10000, Train Loss: 1.5782, Train Accuracy: 0.3616, Val Loss: 1.5795, Val Accuracy: 0.4018 Epoch 1073/10000, Train Loss: 1.5771, Train Accuracy: 0.3884, Val Loss: 1.5795, Val Accuracy: 0.4018 Epoch 1074/10000, Train Loss: 1.5766, Train Accuracy: 0.3884, Val Loss: 1.5794, Val Accuracy: 0.4018 Epoch 1075/10000, Train Loss: 1.5773, Train Accuracy: 0.3661, Val Loss: 1.5793, Val Accuracy: 0.4018 Epoch 1076/10000, Train Loss: 1.5771, Train Accuracy: 0.3929, Val Loss: 1.5793, Val Accuracy: 0.4018 Epoch 1077/10000, Train Loss: 1.5776, Train Accuracy: 0.3739, Val Loss: 1.5792, Val Accuracy: 0.4018 Epoch 1078/10000, Train Loss: 1.5752, Train Accuracy: 0.3761, Val Loss: 1.5791, Val Accuracy: 0.4018 Epoch 1079/10000, Train Loss: 1.5781, Train Accuracy: 0.3705, Val Loss: 1.5790, Val Accuracy: 0.4018 Epoch 1080/10000, Train Loss: 1.5773, Train Accuracy: 0.3705, Val Loss: 1.5789, Val Accuracy: 0.4018 Epoch 1081/10000, Train Loss: 1.5770, Train Accuracy: 0.3672, Val Loss: 1.5789, Val Accuracy: 0.4018 Epoch 1082/10000, Train Loss: 1.5770, Train Accuracy: 0.3839, Val Loss: 1.5788, Val Accuracy: 0.4018 Epoch 1083/10000, Train Loss: 1.5768, Train Accuracy: 0.3795, Val Loss: 1.5787, Val Accuracy: 0.4018 Epoch 1084/10000, Train Loss: 1.5769, Train Accuracy: 0.3750, Val Loss: 1.5786, Val Accuracy: 0.4018 Epoch 1085/10000, Train Loss: 1.5763, Train Accuracy: 0.3672, Val Loss: 1.5786, Val Accuracy: 0.4018 Epoch 1086/10000, Train Loss: 1.5782, Train Accuracy: 0.3750, Val Loss: 1.5785, Val Accuracy: 0.4018 Epoch 1087/10000, Train Loss: 1.5757, Train Accuracy: 0.3761, Val Loss: 1.5784, Val Accuracy: 0.4018 Epoch 1088/10000, Train Loss: 1.5741, Train Accuracy: 0.3739, Val Loss: 1.5783, Val Accuracy: 0.4018 Epoch 1089/10000, Train Loss: 1.5764, Train Accuracy: 0.3661, Val Loss: 1.5782, Val Accuracy: 0.4018 Epoch 1090/10000, Train Loss: 1.5746, Train Accuracy: 0.3750, Val Loss: 1.5781, Val Accuracy: 0.4018 Epoch 1091/10000, Train Loss: 1.5752, Train Accuracy: 0.3694, Val Loss: 1.5781, Val Accuracy: 0.4018 Epoch 1092/10000, Train Loss: 1.5754, Train Accuracy: 0.3627, Val Loss: 1.5780, Val Accuracy: 0.4018 Epoch 1093/10000, Train Loss: 1.5758, Train Accuracy: 0.3571, Val Loss: 1.5779, Val Accuracy: 0.4018 Epoch 1094/10000, Train Loss: 1.5774, Train Accuracy: 0.3650, Val Loss: 1.5778, Val Accuracy: 0.4018 Epoch 1095/10000, Train Loss: 1.5749, Train Accuracy: 0.3783, Val Loss: 1.5777, Val Accuracy: 0.4018 Epoch 1096/10000, Train Loss: 1.5775, Train Accuracy: 0.3672, Val Loss: 1.5776, Val Accuracy: 0.4018 Epoch 1097/10000, Train Loss: 1.5737, Train Accuracy: 0.3694, Val Loss: 1.5776, Val Accuracy: 0.4018 Epoch 1098/10000, Train Loss: 1.5739, Train Accuracy: 0.3862, Val Loss: 1.5775, Val Accuracy: 0.4018 Epoch 1099/10000, Train Loss: 1.5734, Train Accuracy: 0.3672, Val Loss: 1.5774, Val Accuracy: 0.4062 Epoch 1100/10000, Train Loss: 1.5770, Train Accuracy: 0.3873, Val Loss: 1.5773, Val Accuracy: 0.4018 Epoch 1101/10000, Train Loss: 1.5736, Train Accuracy: 0.3683, Val Loss: 1.5772, Val Accuracy: 0.4062 Epoch 1102/10000, Train Loss: 1.5752, Train Accuracy: 0.3828, Val Loss: 1.5772, Val Accuracy: 0.4018 Epoch 1103/10000, Train Loss: 1.5755, Train Accuracy: 0.3929, Val Loss: 1.5771, Val Accuracy: 0.4062 Epoch 1104/10000, Train Loss: 1.5740, Train Accuracy: 0.3728, Val Loss: 1.5770, Val Accuracy: 0.4018 Epoch 1105/10000, Train Loss: 1.5742, Train Accuracy: 0.3906, Val Loss: 1.5769, Val Accuracy: 0.4018 Epoch 1106/10000, Train Loss: 1.5736, Train Accuracy: 0.3650, Val Loss: 1.5768, Val Accuracy: 0.4062 Epoch 1107/10000, Train Loss: 1.5765, Train Accuracy: 0.3594, Val Loss: 1.5767, Val Accuracy: 0.4062 Epoch 1108/10000, Train Loss: 1.5744, Train Accuracy: 0.3594, Val Loss: 1.5767, Val Accuracy: 0.4062 Epoch 1109/10000, Train Loss: 1.5756, Train Accuracy: 0.3705, Val Loss: 1.5766, Val Accuracy: 0.4062 Epoch 1110/10000, Train Loss: 1.5752, Train Accuracy: 0.3516, Val Loss: 1.5765, Val Accuracy: 0.4062 Epoch 1111/10000, Train Loss: 1.5728, Train Accuracy: 0.3806, Val Loss: 1.5764, Val Accuracy: 0.4018 Epoch 1112/10000, Train Loss: 1.5749, Train Accuracy: 0.3717, Val Loss: 1.5763, Val Accuracy: 0.4062 Epoch 1113/10000, Train Loss: 1.5731, Train Accuracy: 0.3739, Val Loss: 1.5762, Val Accuracy: 0.4062 Epoch 1114/10000, Train Loss: 1.5720, Train Accuracy: 0.3761, Val Loss: 1.5761, Val Accuracy: 0.4062 Epoch 1115/10000, Train Loss: 1.5728, Train Accuracy: 0.3895, Val Loss: 1.5760, Val Accuracy: 0.4062 Epoch 1116/10000, Train Loss: 1.5743, Train Accuracy: 0.3839, Val Loss: 1.5759, Val Accuracy: 0.4062 Epoch 1117/10000, Train Loss: 1.5729, Train Accuracy: 0.3605, Val Loss: 1.5758, Val Accuracy: 0.4062 Epoch 1118/10000, Train Loss: 1.5713, Train Accuracy: 0.3895, Val Loss: 1.5758, Val Accuracy: 0.4062 Epoch 1119/10000, Train Loss: 1.5731, Train Accuracy: 0.3783, Val Loss: 1.5757, Val Accuracy: 0.4062 Epoch 1120/10000, Train Loss: 1.5728, Train Accuracy: 0.3839, Val Loss: 1.5756, Val Accuracy: 0.4062 Epoch 1121/10000, Train Loss: 1.5743, Train Accuracy: 0.3750, Val Loss: 1.5755, Val Accuracy: 0.4062 Epoch 1122/10000, Train Loss: 1.5743, Train Accuracy: 0.3683, Val Loss: 1.5754, Val Accuracy: 0.4062 Epoch 1123/10000, Train Loss: 1.5735, Train Accuracy: 0.3772, Val Loss: 1.5753, Val Accuracy: 0.4062 Epoch 1124/10000, Train Loss: 1.5752, Train Accuracy: 0.3717, Val Loss: 1.5752, Val Accuracy: 0.4062 Epoch 1125/10000, Train Loss: 1.5720, Train Accuracy: 0.3895, Val Loss: 1.5751, Val Accuracy: 0.4062 Epoch 1126/10000, Train Loss: 1.5736, Train Accuracy: 0.3705, Val Loss: 1.5751, Val Accuracy: 0.4062 Epoch 1127/10000, Train Loss: 1.5724, Train Accuracy: 0.3817, Val Loss: 1.5750, Val Accuracy: 0.4062 Epoch 1128/10000, Train Loss: 1.5702, Train Accuracy: 0.3772, Val Loss: 1.5749, Val Accuracy: 0.4062 Epoch 1129/10000, Train Loss: 1.5732, Train Accuracy: 0.3694, Val Loss: 1.5748, Val Accuracy: 0.4062 Epoch 1130/10000, Train Loss: 1.5686, Train Accuracy: 0.3862, Val Loss: 1.5747, Val Accuracy: 0.4062 Epoch 1131/10000, Train Loss: 1.5718, Train Accuracy: 0.3772, Val Loss: 1.5747, Val Accuracy: 0.4107 Epoch 1132/10000, Train Loss: 1.5727, Train Accuracy: 0.3806, Val Loss: 1.5745, Val Accuracy: 0.4107 Epoch 1133/10000, Train Loss: 1.5723, Train Accuracy: 0.3627, Val Loss: 1.5745, Val Accuracy: 0.4107 Epoch 1134/10000, Train Loss: 1.5744, Train Accuracy: 0.3705, Val Loss: 1.5744, Val Accuracy: 0.4107 Epoch 1135/10000, Train Loss: 1.5710, Train Accuracy: 0.4062, Val Loss: 1.5743, Val Accuracy: 0.4107 Epoch 1136/10000, Train Loss: 1.5696, Train Accuracy: 0.3828, Val Loss: 1.5742, Val Accuracy: 0.4107 Epoch 1137/10000, Train Loss: 1.5713, Train Accuracy: 0.3806, Val Loss: 1.5741, Val Accuracy: 0.4107 Epoch 1138/10000, Train Loss: 1.5712, Train Accuracy: 0.3884, Val Loss: 1.5740, Val Accuracy: 0.4107 Epoch 1139/10000, Train Loss: 1.5700, Train Accuracy: 0.3795, Val Loss: 1.5739, Val Accuracy: 0.4107 Epoch 1140/10000, Train Loss: 1.5707, Train Accuracy: 0.3761, Val Loss: 1.5738, Val Accuracy: 0.4107 Epoch 1141/10000, Train Loss: 1.5710, Train Accuracy: 0.3884, Val Loss: 1.5737, Val Accuracy: 0.4107 Epoch 1142/10000, Train Loss: 1.5689, Train Accuracy: 0.3806, Val Loss: 1.5736, Val Accuracy: 0.4107 Epoch 1143/10000, Train Loss: 1.5706, Train Accuracy: 0.3828, Val Loss: 1.5736, Val Accuracy: 0.4107 Epoch 1144/10000, Train Loss: 1.5722, Train Accuracy: 0.3560, Val Loss: 1.5735, Val Accuracy: 0.4107 Epoch 1145/10000, Train Loss: 1.5704, Train Accuracy: 0.3795, Val Loss: 1.5734, Val Accuracy: 0.4107 Epoch 1146/10000, Train Loss: 1.5715, Train Accuracy: 0.3817, Val Loss: 1.5733, Val Accuracy: 0.4107 Epoch 1147/10000, Train Loss: 1.5699, Train Accuracy: 0.3783, Val Loss: 1.5732, Val Accuracy: 0.4107 Epoch 1148/10000, Train Loss: 1.5727, Train Accuracy: 0.3895, Val Loss: 1.5731, Val Accuracy: 0.4107 Epoch 1149/10000, Train Loss: 1.5711, Train Accuracy: 0.3705, Val Loss: 1.5730, Val Accuracy: 0.4107 Epoch 1150/10000, Train Loss: 1.5721, Train Accuracy: 0.3862, Val Loss: 1.5729, Val Accuracy: 0.4062 Epoch 1151/10000, Train Loss: 1.5684, Train Accuracy: 0.3917, Val Loss: 1.5728, Val Accuracy: 0.4062 Epoch 1152/10000, Train Loss: 1.5668, Train Accuracy: 0.3761, Val Loss: 1.5727, Val Accuracy: 0.4062 Epoch 1153/10000, Train Loss: 1.5717, Train Accuracy: 0.3616, Val Loss: 1.5726, Val Accuracy: 0.4062 Epoch 1154/10000, Train Loss: 1.5694, Train Accuracy: 0.4018, Val Loss: 1.5725, Val Accuracy: 0.4062 Epoch 1155/10000, Train Loss: 1.5679, Train Accuracy: 0.3973, Val Loss: 1.5724, Val Accuracy: 0.4062 Epoch 1156/10000, Train Loss: 1.5687, Train Accuracy: 0.3728, Val Loss: 1.5723, Val Accuracy: 0.4062 Epoch 1157/10000, Train Loss: 1.5684, Train Accuracy: 0.3728, Val Loss: 1.5722, Val Accuracy: 0.4062 Epoch 1158/10000, Train Loss: 1.5697, Train Accuracy: 0.3806, Val Loss: 1.5721, Val Accuracy: 0.4062 Epoch 1159/10000, Train Loss: 1.5716, Train Accuracy: 0.3717, Val Loss: 1.5720, Val Accuracy: 0.4062 Epoch 1160/10000, Train Loss: 1.5708, Train Accuracy: 0.3817, Val Loss: 1.5719, Val Accuracy: 0.4062 Epoch 1161/10000, Train Loss: 1.5706, Train Accuracy: 0.3750, Val Loss: 1.5718, Val Accuracy: 0.4062 Epoch 1162/10000, Train Loss: 1.5690, Train Accuracy: 0.3873, Val Loss: 1.5717, Val Accuracy: 0.4062 Epoch 1163/10000, Train Loss: 1.5695, Train Accuracy: 0.3694, Val Loss: 1.5717, Val Accuracy: 0.4062 Epoch 1164/10000, Train Loss: 1.5671, Train Accuracy: 0.4007, Val Loss: 1.5716, Val Accuracy: 0.4062 Epoch 1165/10000, Train Loss: 1.5684, Train Accuracy: 0.3929, Val Loss: 1.5715, Val Accuracy: 0.4062 Epoch 1166/10000, Train Loss: 1.5687, Train Accuracy: 0.3828, Val Loss: 1.5714, Val Accuracy: 0.4062 Epoch 1167/10000, Train Loss: 1.5718, Train Accuracy: 0.3661, Val Loss: 1.5713, Val Accuracy: 0.4062 Epoch 1168/10000, Train Loss: 1.5682, Train Accuracy: 0.3951, Val Loss: 1.5711, Val Accuracy: 0.4062 Epoch 1169/10000, Train Loss: 1.5706, Train Accuracy: 0.3638, Val Loss: 1.5711, Val Accuracy: 0.4062 Epoch 1170/10000, Train Loss: 1.5683, Train Accuracy: 0.3895, Val Loss: 1.5710, Val Accuracy: 0.4062 Epoch 1171/10000, Train Loss: 1.5697, Train Accuracy: 0.3739, Val Loss: 1.5708, Val Accuracy: 0.4062 Epoch 1172/10000, Train Loss: 1.5686, Train Accuracy: 0.3973, Val Loss: 1.5708, Val Accuracy: 0.4062 Epoch 1173/10000, Train Loss: 1.5691, Train Accuracy: 0.3873, Val Loss: 1.5707, Val Accuracy: 0.4062 Epoch 1174/10000, Train Loss: 1.5703, Train Accuracy: 0.3772, Val Loss: 1.5706, Val Accuracy: 0.4062 Epoch 1175/10000, Train Loss: 1.5686, Train Accuracy: 0.3638, Val Loss: 1.5705, Val Accuracy: 0.4062 Epoch 1176/10000, Train Loss: 1.5654, Train Accuracy: 0.3761, Val Loss: 1.5704, Val Accuracy: 0.4107 Epoch 1177/10000, Train Loss: 1.5648, Train Accuracy: 0.3906, Val Loss: 1.5703, Val Accuracy: 0.4062 Epoch 1178/10000, Train Loss: 1.5686, Train Accuracy: 0.3717, Val Loss: 1.5702, Val Accuracy: 0.4107 Epoch 1179/10000, Train Loss: 1.5672, Train Accuracy: 0.3761, Val Loss: 1.5701, Val Accuracy: 0.4062 Epoch 1180/10000, Train Loss: 1.5669, Train Accuracy: 0.3783, Val Loss: 1.5700, Val Accuracy: 0.4107 Epoch 1181/10000, Train Loss: 1.5675, Train Accuracy: 0.3739, Val Loss: 1.5699, Val Accuracy: 0.4107 Epoch 1182/10000, Train Loss: 1.5672, Train Accuracy: 0.3828, Val Loss: 1.5698, Val Accuracy: 0.4107 Epoch 1183/10000, Train Loss: 1.5662, Train Accuracy: 0.3895, Val Loss: 1.5697, Val Accuracy: 0.4107 Epoch 1184/10000, Train Loss: 1.5680, Train Accuracy: 0.3839, Val Loss: 1.5696, Val Accuracy: 0.4107 Epoch 1185/10000, Train Loss: 1.5658, Train Accuracy: 0.3895, Val Loss: 1.5695, Val Accuracy: 0.4107 Epoch 1186/10000, Train Loss: 1.5665, Train Accuracy: 0.3694, Val Loss: 1.5694, Val Accuracy: 0.4107 Epoch 1187/10000, Train Loss: 1.5677, Train Accuracy: 0.3683, Val Loss: 1.5693, Val Accuracy: 0.4107 Epoch 1188/10000, Train Loss: 1.5685, Train Accuracy: 0.3638, Val Loss: 1.5692, Val Accuracy: 0.4107 Epoch 1189/10000, Train Loss: 1.5664, Train Accuracy: 0.3862, Val Loss: 1.5691, Val Accuracy: 0.4107 Epoch 1190/10000, Train Loss: 1.5638, Train Accuracy: 0.4051, Val Loss: 1.5690, Val Accuracy: 0.4107 Epoch 1191/10000, Train Loss: 1.5657, Train Accuracy: 0.3895, Val Loss: 1.5689, Val Accuracy: 0.4107 Epoch 1192/10000, Train Loss: 1.5670, Train Accuracy: 0.3873, Val Loss: 1.5688, Val Accuracy: 0.4107 Epoch 1193/10000, Train Loss: 1.5668, Train Accuracy: 0.3817, Val Loss: 1.5687, Val Accuracy: 0.4107 Epoch 1194/10000, Train Loss: 1.5650, Train Accuracy: 0.3839, Val Loss: 1.5686, Val Accuracy: 0.4107 Epoch 1195/10000, Train Loss: 1.5651, Train Accuracy: 0.3850, Val Loss: 1.5684, Val Accuracy: 0.4152 Epoch 1196/10000, Train Loss: 1.5649, Train Accuracy: 0.3940, Val Loss: 1.5683, Val Accuracy: 0.4107 Epoch 1197/10000, Train Loss: 1.5669, Train Accuracy: 0.3884, Val Loss: 1.5682, Val Accuracy: 0.4107 Epoch 1198/10000, Train Loss: 1.5663, Train Accuracy: 0.3873, Val Loss: 1.5681, Val Accuracy: 0.4107 Epoch 1199/10000, Train Loss: 1.5656, Train Accuracy: 0.3839, Val Loss: 1.5680, Val Accuracy: 0.4107 Epoch 1200/10000, Train Loss: 1.5660, Train Accuracy: 0.3739, Val Loss: 1.5679, Val Accuracy: 0.4107 Epoch 1201/10000, Train Loss: 1.5682, Train Accuracy: 0.3728, Val Loss: 1.5678, Val Accuracy: 0.4107 Epoch 1202/10000, Train Loss: 1.5613, Train Accuracy: 0.3984, Val Loss: 1.5677, Val Accuracy: 0.4107 Epoch 1203/10000, Train Loss: 1.5678, Train Accuracy: 0.3817, Val Loss: 1.5676, Val Accuracy: 0.4152 Epoch 1204/10000, Train Loss: 1.5643, Train Accuracy: 0.3929, Val Loss: 1.5675, Val Accuracy: 0.4107 Epoch 1205/10000, Train Loss: 1.5625, Train Accuracy: 0.3873, Val Loss: 1.5674, Val Accuracy: 0.4152 Epoch 1206/10000, Train Loss: 1.5647, Train Accuracy: 0.3761, Val Loss: 1.5673, Val Accuracy: 0.4107 Epoch 1207/10000, Train Loss: 1.5630, Train Accuracy: 0.3884, Val Loss: 1.5671, Val Accuracy: 0.4152 Epoch 1208/10000, Train Loss: 1.5620, Train Accuracy: 0.3906, Val Loss: 1.5670, Val Accuracy: 0.4152 Epoch 1209/10000, Train Loss: 1.5630, Train Accuracy: 0.3962, Val Loss: 1.5669, Val Accuracy: 0.4152 Epoch 1210/10000, Train Loss: 1.5635, Train Accuracy: 0.4007, Val Loss: 1.5667, Val Accuracy: 0.4152 Epoch 1211/10000, Train Loss: 1.5648, Train Accuracy: 0.3873, Val Loss: 1.5666, Val Accuracy: 0.4152 Epoch 1212/10000, Train Loss: 1.5626, Train Accuracy: 0.4051, Val Loss: 1.5665, Val Accuracy: 0.4152 Epoch 1213/10000, Train Loss: 1.5642, Train Accuracy: 0.3772, Val Loss: 1.5664, Val Accuracy: 0.4152 Epoch 1214/10000, Train Loss: 1.5643, Train Accuracy: 0.3783, Val Loss: 1.5663, Val Accuracy: 0.4152 Epoch 1215/10000, Train Loss: 1.5632, Train Accuracy: 0.3951, Val Loss: 1.5662, Val Accuracy: 0.4152 Epoch 1216/10000, Train Loss: 1.5665, Train Accuracy: 0.3795, Val Loss: 1.5661, Val Accuracy: 0.4152 Epoch 1217/10000, Train Loss: 1.5632, Train Accuracy: 0.3951, Val Loss: 1.5659, Val Accuracy: 0.4107 Epoch 1218/10000, Train Loss: 1.5636, Train Accuracy: 0.3828, Val Loss: 1.5658, Val Accuracy: 0.4107 Epoch 1219/10000, Train Loss: 1.5625, Train Accuracy: 0.4085, Val Loss: 1.5657, Val Accuracy: 0.4107 Epoch 1220/10000, Train Loss: 1.5624, Train Accuracy: 0.3783, Val Loss: 1.5656, Val Accuracy: 0.4107 Epoch 1221/10000, Train Loss: 1.5644, Train Accuracy: 0.3828, Val Loss: 1.5655, Val Accuracy: 0.4107 Epoch 1222/10000, Train Loss: 1.5609, Train Accuracy: 0.3772, Val Loss: 1.5654, Val Accuracy: 0.4107 Epoch 1223/10000, Train Loss: 1.5626, Train Accuracy: 0.3806, Val Loss: 1.5652, Val Accuracy: 0.4152 Epoch 1224/10000, Train Loss: 1.5639, Train Accuracy: 0.3783, Val Loss: 1.5651, Val Accuracy: 0.4196 Epoch 1225/10000, Train Loss: 1.5623, Train Accuracy: 0.3850, Val Loss: 1.5650, Val Accuracy: 0.4196 Epoch 1226/10000, Train Loss: 1.5603, Train Accuracy: 0.3895, Val Loss: 1.5649, Val Accuracy: 0.4196 Epoch 1227/10000, Train Loss: 1.5617, Train Accuracy: 0.3884, Val Loss: 1.5647, Val Accuracy: 0.4196 Epoch 1228/10000, Train Loss: 1.5611, Train Accuracy: 0.3839, Val Loss: 1.5647, Val Accuracy: 0.4196 Epoch 1229/10000, Train Loss: 1.5631, Train Accuracy: 0.3973, Val Loss: 1.5645, Val Accuracy: 0.4196 Epoch 1230/10000, Train Loss: 1.5634, Train Accuracy: 0.3493, Val Loss: 1.5645, Val Accuracy: 0.4196 Epoch 1231/10000, Train Loss: 1.5596, Train Accuracy: 0.3996, Val Loss: 1.5644, Val Accuracy: 0.4196 Epoch 1232/10000, Train Loss: 1.5610, Train Accuracy: 0.3761, Val Loss: 1.5642, Val Accuracy: 0.4196 Epoch 1233/10000, Train Loss: 1.5632, Train Accuracy: 0.3661, Val Loss: 1.5641, Val Accuracy: 0.4196 Epoch 1234/10000, Train Loss: 1.5610, Train Accuracy: 0.3984, Val Loss: 1.5640, Val Accuracy: 0.4152 Epoch 1235/10000, Train Loss: 1.5621, Train Accuracy: 0.3862, Val Loss: 1.5638, Val Accuracy: 0.4152 Epoch 1236/10000, Train Loss: 1.5615, Train Accuracy: 0.3906, Val Loss: 1.5637, Val Accuracy: 0.4152 Epoch 1237/10000, Train Loss: 1.5611, Train Accuracy: 0.3817, Val Loss: 1.5636, Val Accuracy: 0.4152 Epoch 1238/10000, Train Loss: 1.5617, Train Accuracy: 0.3817, Val Loss: 1.5635, Val Accuracy: 0.4152 Epoch 1239/10000, Train Loss: 1.5585, Train Accuracy: 0.3917, Val Loss: 1.5633, Val Accuracy: 0.4152 Epoch 1240/10000, Train Loss: 1.5601, Train Accuracy: 0.4029, Val Loss: 1.5632, Val Accuracy: 0.4196 Epoch 1241/10000, Train Loss: 1.5596, Train Accuracy: 0.3817, Val Loss: 1.5631, Val Accuracy: 0.4196 Epoch 1242/10000, Train Loss: 1.5592, Train Accuracy: 0.3984, Val Loss: 1.5630, Val Accuracy: 0.4241 Epoch 1243/10000, Train Loss: 1.5620, Train Accuracy: 0.3772, Val Loss: 1.5629, Val Accuracy: 0.4241 Epoch 1244/10000, Train Loss: 1.5602, Train Accuracy: 0.3817, Val Loss: 1.5627, Val Accuracy: 0.4241 Epoch 1245/10000, Train Loss: 1.5601, Train Accuracy: 0.3906, Val Loss: 1.5626, Val Accuracy: 0.4196 Epoch 1246/10000, Train Loss: 1.5592, Train Accuracy: 0.3862, Val Loss: 1.5625, Val Accuracy: 0.4196 Epoch 1247/10000, Train Loss: 1.5590, Train Accuracy: 0.4141, Val Loss: 1.5624, Val Accuracy: 0.4196 Epoch 1248/10000, Train Loss: 1.5586, Train Accuracy: 0.3895, Val Loss: 1.5623, Val Accuracy: 0.4196 Epoch 1249/10000, Train Loss: 1.5581, Train Accuracy: 0.3862, Val Loss: 1.5621, Val Accuracy: 0.4241 Epoch 1250/10000, Train Loss: 1.5596, Train Accuracy: 0.4029, Val Loss: 1.5620, Val Accuracy: 0.4241 Epoch 1251/10000, Train Loss: 1.5600, Train Accuracy: 0.3873, Val Loss: 1.5619, Val Accuracy: 0.4241 Epoch 1252/10000, Train Loss: 1.5582, Train Accuracy: 0.3694, Val Loss: 1.5618, Val Accuracy: 0.4241 Epoch 1253/10000, Train Loss: 1.5577, Train Accuracy: 0.3884, Val Loss: 1.5617, Val Accuracy: 0.4241 Epoch 1254/10000, Train Loss: 1.5573, Train Accuracy: 0.4074, Val Loss: 1.5616, Val Accuracy: 0.4241 Epoch 1255/10000, Train Loss: 1.5602, Train Accuracy: 0.3884, Val Loss: 1.5614, Val Accuracy: 0.4241 Epoch 1256/10000, Train Loss: 1.5589, Train Accuracy: 0.3850, Val Loss: 1.5613, Val Accuracy: 0.4241 Epoch 1257/10000, Train Loss: 1.5564, Train Accuracy: 0.4163, Val Loss: 1.5612, Val Accuracy: 0.4196 Epoch 1258/10000, Train Loss: 1.5590, Train Accuracy: 0.3895, Val Loss: 1.5611, Val Accuracy: 0.4196 Epoch 1259/10000, Train Loss: 1.5559, Train Accuracy: 0.4141, Val Loss: 1.5609, Val Accuracy: 0.4241 Epoch 1260/10000, Train Loss: 1.5582, Train Accuracy: 0.3940, Val Loss: 1.5608, Val Accuracy: 0.4241 Epoch 1261/10000, Train Loss: 1.5573, Train Accuracy: 0.4018, Val Loss: 1.5607, Val Accuracy: 0.4241 Epoch 1262/10000, Train Loss: 1.5558, Train Accuracy: 0.4040, Val Loss: 1.5605, Val Accuracy: 0.4241 Epoch 1263/10000, Train Loss: 1.5574, Train Accuracy: 0.3962, Val Loss: 1.5604, Val Accuracy: 0.4241 Epoch 1264/10000, Train Loss: 1.5604, Train Accuracy: 0.3917, Val Loss: 1.5603, Val Accuracy: 0.4241 Epoch 1265/10000, Train Loss: 1.5531, Train Accuracy: 0.3962, Val Loss: 1.5602, Val Accuracy: 0.4286 Epoch 1266/10000, Train Loss: 1.5599, Train Accuracy: 0.3917, Val Loss: 1.5600, Val Accuracy: 0.4241 Epoch 1267/10000, Train Loss: 1.5584, Train Accuracy: 0.3951, Val Loss: 1.5599, Val Accuracy: 0.4196 Epoch 1268/10000, Train Loss: 1.5556, Train Accuracy: 0.3996, Val Loss: 1.5598, Val Accuracy: 0.4196 Epoch 1269/10000, Train Loss: 1.5577, Train Accuracy: 0.4029, Val Loss: 1.5597, Val Accuracy: 0.4196 Epoch 1270/10000, Train Loss: 1.5552, Train Accuracy: 0.3884, Val Loss: 1.5596, Val Accuracy: 0.4196 Epoch 1271/10000, Train Loss: 1.5570, Train Accuracy: 0.4062, Val Loss: 1.5595, Val Accuracy: 0.4196 Epoch 1272/10000, Train Loss: 1.5598, Train Accuracy: 0.3839, Val Loss: 1.5594, Val Accuracy: 0.4196 Epoch 1273/10000, Train Loss: 1.5572, Train Accuracy: 0.4062, Val Loss: 1.5592, Val Accuracy: 0.4196 Epoch 1274/10000, Train Loss: 1.5577, Train Accuracy: 0.3895, Val Loss: 1.5591, Val Accuracy: 0.4196 Epoch 1275/10000, Train Loss: 1.5551, Train Accuracy: 0.3951, Val Loss: 1.5590, Val Accuracy: 0.4196 Epoch 1276/10000, Train Loss: 1.5568, Train Accuracy: 0.3973, Val Loss: 1.5588, Val Accuracy: 0.4196 Epoch 1277/10000, Train Loss: 1.5555, Train Accuracy: 0.3873, Val Loss: 1.5587, Val Accuracy: 0.4196 Epoch 1278/10000, Train Loss: 1.5553, Train Accuracy: 0.4129, Val Loss: 1.5586, Val Accuracy: 0.4196 Epoch 1279/10000, Train Loss: 1.5544, Train Accuracy: 0.3940, Val Loss: 1.5584, Val Accuracy: 0.4286 Epoch 1280/10000, Train Loss: 1.5539, Train Accuracy: 0.3828, Val Loss: 1.5583, Val Accuracy: 0.4196 Epoch 1281/10000, Train Loss: 1.5557, Train Accuracy: 0.3940, Val Loss: 1.5582, Val Accuracy: 0.4286 Epoch 1282/10000, Train Loss: 1.5573, Train Accuracy: 0.3873, Val Loss: 1.5580, Val Accuracy: 0.4286 Epoch 1283/10000, Train Loss: 1.5548, Train Accuracy: 0.4096, Val Loss: 1.5579, Val Accuracy: 0.4286 Epoch 1284/10000, Train Loss: 1.5560, Train Accuracy: 0.4040, Val Loss: 1.5577, Val Accuracy: 0.4286 Epoch 1285/10000, Train Loss: 1.5527, Train Accuracy: 0.3951, Val Loss: 1.5576, Val Accuracy: 0.4286 Epoch 1286/10000, Train Loss: 1.5558, Train Accuracy: 0.3984, Val Loss: 1.5575, Val Accuracy: 0.4286 Epoch 1287/10000, Train Loss: 1.5559, Train Accuracy: 0.3951, Val Loss: 1.5573, Val Accuracy: 0.4330 Epoch 1288/10000, Train Loss: 1.5537, Train Accuracy: 0.4018, Val Loss: 1.5572, Val Accuracy: 0.4286 Epoch 1289/10000, Train Loss: 1.5565, Train Accuracy: 0.3795, Val Loss: 1.5571, Val Accuracy: 0.4286 Epoch 1290/10000, Train Loss: 1.5546, Train Accuracy: 0.3973, Val Loss: 1.5569, Val Accuracy: 0.4330 Epoch 1291/10000, Train Loss: 1.5546, Train Accuracy: 0.3828, Val Loss: 1.5568, Val Accuracy: 0.4286 Epoch 1292/10000, Train Loss: 1.5513, Train Accuracy: 0.4129, Val Loss: 1.5567, Val Accuracy: 0.4286 Epoch 1293/10000, Train Loss: 1.5549, Train Accuracy: 0.3873, Val Loss: 1.5566, Val Accuracy: 0.4286 Epoch 1294/10000, Train Loss: 1.5525, Train Accuracy: 0.3996, Val Loss: 1.5564, Val Accuracy: 0.4286 Epoch 1295/10000, Train Loss: 1.5504, Train Accuracy: 0.3940, Val Loss: 1.5563, Val Accuracy: 0.4286 Epoch 1296/10000, Train Loss: 1.5530, Train Accuracy: 0.4029, Val Loss: 1.5562, Val Accuracy: 0.4286 Epoch 1297/10000, Train Loss: 1.5532, Train Accuracy: 0.3862, Val Loss: 1.5560, Val Accuracy: 0.4241 Epoch 1298/10000, Train Loss: 1.5566, Train Accuracy: 0.3940, Val Loss: 1.5559, Val Accuracy: 0.4241 Epoch 1299/10000, Train Loss: 1.5522, Train Accuracy: 0.4040, Val Loss: 1.5557, Val Accuracy: 0.4286 Epoch 1300/10000, Train Loss: 1.5509, Train Accuracy: 0.3884, Val Loss: 1.5556, Val Accuracy: 0.4286 Epoch 1301/10000, Train Loss: 1.5500, Train Accuracy: 0.4196, Val Loss: 1.5554, Val Accuracy: 0.4241 Epoch 1302/10000, Train Loss: 1.5526, Train Accuracy: 0.3850, Val Loss: 1.5553, Val Accuracy: 0.4241 Epoch 1303/10000, Train Loss: 1.5531, Train Accuracy: 0.3828, Val Loss: 1.5551, Val Accuracy: 0.4241 Epoch 1304/10000, Train Loss: 1.5554, Train Accuracy: 0.3962, Val Loss: 1.5550, Val Accuracy: 0.4241 Epoch 1305/10000, Train Loss: 1.5526, Train Accuracy: 0.3895, Val Loss: 1.5549, Val Accuracy: 0.4241 Epoch 1306/10000, Train Loss: 1.5517, Train Accuracy: 0.4018, Val Loss: 1.5547, Val Accuracy: 0.4241 Epoch 1307/10000, Train Loss: 1.5533, Train Accuracy: 0.4096, Val Loss: 1.5546, Val Accuracy: 0.4241 Epoch 1308/10000, Train Loss: 1.5510, Train Accuracy: 0.4007, Val Loss: 1.5545, Val Accuracy: 0.4241 Epoch 1309/10000, Train Loss: 1.5535, Train Accuracy: 0.3862, Val Loss: 1.5543, Val Accuracy: 0.4241 Epoch 1310/10000, Train Loss: 1.5501, Train Accuracy: 0.4096, Val Loss: 1.5542, Val Accuracy: 0.4241 Epoch 1311/10000, Train Loss: 1.5534, Train Accuracy: 0.3951, Val Loss: 1.5541, Val Accuracy: 0.4241 Epoch 1312/10000, Train Loss: 1.5516, Train Accuracy: 0.4062, Val Loss: 1.5540, Val Accuracy: 0.4196 Epoch 1313/10000, Train Loss: 1.5492, Train Accuracy: 0.4196, Val Loss: 1.5538, Val Accuracy: 0.4241 Epoch 1314/10000, Train Loss: 1.5508, Train Accuracy: 0.3940, Val Loss: 1.5537, Val Accuracy: 0.4241 Epoch 1315/10000, Train Loss: 1.5525, Train Accuracy: 0.4007, Val Loss: 1.5535, Val Accuracy: 0.4241 Epoch 1316/10000, Train Loss: 1.5503, Train Accuracy: 0.4018, Val Loss: 1.5534, Val Accuracy: 0.4241 Epoch 1317/10000, Train Loss: 1.5506, Train Accuracy: 0.3984, Val Loss: 1.5533, Val Accuracy: 0.4241 Epoch 1318/10000, Train Loss: 1.5523, Train Accuracy: 0.3895, Val Loss: 1.5531, Val Accuracy: 0.4196 Epoch 1319/10000, Train Loss: 1.5516, Train Accuracy: 0.4007, Val Loss: 1.5530, Val Accuracy: 0.4241 Epoch 1320/10000, Train Loss: 1.5521, Train Accuracy: 0.3906, Val Loss: 1.5528, Val Accuracy: 0.4196 Epoch 1321/10000, Train Loss: 1.5514, Train Accuracy: 0.3806, Val Loss: 1.5527, Val Accuracy: 0.4196 Epoch 1322/10000, Train Loss: 1.5505, Train Accuracy: 0.4085, Val Loss: 1.5526, Val Accuracy: 0.4196 Epoch 1323/10000, Train Loss: 1.5516, Train Accuracy: 0.3739, Val Loss: 1.5525, Val Accuracy: 0.4196 Epoch 1324/10000, Train Loss: 1.5506, Train Accuracy: 0.3984, Val Loss: 1.5524, Val Accuracy: 0.4196 Epoch 1325/10000, Train Loss: 1.5504, Train Accuracy: 0.4007, Val Loss: 1.5523, Val Accuracy: 0.4196 Epoch 1326/10000, Train Loss: 1.5506, Train Accuracy: 0.3929, Val Loss: 1.5521, Val Accuracy: 0.4196 Epoch 1327/10000, Train Loss: 1.5518, Train Accuracy: 0.3750, Val Loss: 1.5520, Val Accuracy: 0.4196 Epoch 1328/10000, Train Loss: 1.5480, Train Accuracy: 0.3895, Val Loss: 1.5518, Val Accuracy: 0.4196 Epoch 1329/10000, Train Loss: 1.5493, Train Accuracy: 0.3884, Val Loss: 1.5517, Val Accuracy: 0.4196 Epoch 1330/10000, Train Loss: 1.5480, Train Accuracy: 0.4174, Val Loss: 1.5515, Val Accuracy: 0.4196 Epoch 1331/10000, Train Loss: 1.5469, Train Accuracy: 0.4174, Val Loss: 1.5514, Val Accuracy: 0.4241 Epoch 1332/10000, Train Loss: 1.5501, Train Accuracy: 0.4029, Val Loss: 1.5512, Val Accuracy: 0.4241 Epoch 1333/10000, Train Loss: 1.5491, Train Accuracy: 0.4152, Val Loss: 1.5510, Val Accuracy: 0.4241 Epoch 1334/10000, Train Loss: 1.5450, Train Accuracy: 0.4118, Val Loss: 1.5509, Val Accuracy: 0.4196 Epoch 1335/10000, Train Loss: 1.5465, Train Accuracy: 0.3940, Val Loss: 1.5508, Val Accuracy: 0.4196 Epoch 1336/10000, Train Loss: 1.5479, Train Accuracy: 0.3783, Val Loss: 1.5506, Val Accuracy: 0.4196 Epoch 1337/10000, Train Loss: 1.5484, Train Accuracy: 0.3996, Val Loss: 1.5505, Val Accuracy: 0.4152 Epoch 1338/10000, Train Loss: 1.5451, Train Accuracy: 0.3929, Val Loss: 1.5503, Val Accuracy: 0.4152 Epoch 1339/10000, Train Loss: 1.5491, Train Accuracy: 0.3906, Val Loss: 1.5501, Val Accuracy: 0.4152 Epoch 1340/10000, Train Loss: 1.5483, Train Accuracy: 0.4007, Val Loss: 1.5499, Val Accuracy: 0.4152 Epoch 1341/10000, Train Loss: 1.5474, Train Accuracy: 0.4029, Val Loss: 1.5498, Val Accuracy: 0.4152 Epoch 1342/10000, Train Loss: 1.5460, Train Accuracy: 0.3906, Val Loss: 1.5497, Val Accuracy: 0.4152 Epoch 1343/10000, Train Loss: 1.5496, Train Accuracy: 0.3895, Val Loss: 1.5495, Val Accuracy: 0.4152 Epoch 1344/10000, Train Loss: 1.5479, Train Accuracy: 0.3839, Val Loss: 1.5494, Val Accuracy: 0.4152 Epoch 1345/10000, Train Loss: 1.5474, Train Accuracy: 0.3817, Val Loss: 1.5492, Val Accuracy: 0.4152 Epoch 1346/10000, Train Loss: 1.5488, Train Accuracy: 0.4029, Val Loss: 1.5491, Val Accuracy: 0.4107 Epoch 1347/10000, Train Loss: 1.5454, Train Accuracy: 0.4040, Val Loss: 1.5490, Val Accuracy: 0.4107 Epoch 1348/10000, Train Loss: 1.5480, Train Accuracy: 0.3940, Val Loss: 1.5488, Val Accuracy: 0.4107 Epoch 1349/10000, Train Loss: 1.5472, Train Accuracy: 0.4029, Val Loss: 1.5487, Val Accuracy: 0.4107 Epoch 1350/10000, Train Loss: 1.5446, Train Accuracy: 0.4129, Val Loss: 1.5485, Val Accuracy: 0.4107 Epoch 1351/10000, Train Loss: 1.5483, Train Accuracy: 0.3884, Val Loss: 1.5484, Val Accuracy: 0.4107 Epoch 1352/10000, Train Loss: 1.5452, Train Accuracy: 0.3973, Val Loss: 1.5482, Val Accuracy: 0.4062 Epoch 1353/10000, Train Loss: 1.5465, Train Accuracy: 0.3895, Val Loss: 1.5481, Val Accuracy: 0.4062 Epoch 1354/10000, Train Loss: 1.5457, Train Accuracy: 0.4096, Val Loss: 1.5479, Val Accuracy: 0.4062 Epoch 1355/10000, Train Loss: 1.5455, Train Accuracy: 0.3839, Val Loss: 1.5478, Val Accuracy: 0.4062 Epoch 1356/10000, Train Loss: 1.5459, Train Accuracy: 0.4129, Val Loss: 1.5476, Val Accuracy: 0.4062 Epoch 1357/10000, Train Loss: 1.5465, Train Accuracy: 0.4040, Val Loss: 1.5475, Val Accuracy: 0.4062 Epoch 1358/10000, Train Loss: 1.5439, Train Accuracy: 0.4051, Val Loss: 1.5474, Val Accuracy: 0.4062 Epoch 1359/10000, Train Loss: 1.5454, Train Accuracy: 0.3973, Val Loss: 1.5471, Val Accuracy: 0.4062 Epoch 1360/10000, Train Loss: 1.5441, Train Accuracy: 0.3806, Val Loss: 1.5470, Val Accuracy: 0.4018 Epoch 1361/10000, Train Loss: 1.5468, Train Accuracy: 0.4141, Val Loss: 1.5469, Val Accuracy: 0.4062 Epoch 1362/10000, Train Loss: 1.5425, Train Accuracy: 0.4029, Val Loss: 1.5467, Val Accuracy: 0.4018 Epoch 1363/10000, Train Loss: 1.5472, Train Accuracy: 0.3862, Val Loss: 1.5466, Val Accuracy: 0.4018 Epoch 1364/10000, Train Loss: 1.5459, Train Accuracy: 0.3906, Val Loss: 1.5464, Val Accuracy: 0.4018 Epoch 1365/10000, Train Loss: 1.5415, Train Accuracy: 0.4085, Val Loss: 1.5462, Val Accuracy: 0.4018 Epoch 1366/10000, Train Loss: 1.5429, Train Accuracy: 0.4275, Val Loss: 1.5461, Val Accuracy: 0.4018 Epoch 1367/10000, Train Loss: 1.5436, Train Accuracy: 0.4185, Val Loss: 1.5460, Val Accuracy: 0.4018 Epoch 1368/10000, Train Loss: 1.5414, Train Accuracy: 0.4275, Val Loss: 1.5457, Val Accuracy: 0.4018 Epoch 1369/10000, Train Loss: 1.5431, Train Accuracy: 0.4118, Val Loss: 1.5456, Val Accuracy: 0.4062 Epoch 1370/10000, Train Loss: 1.5432, Train Accuracy: 0.4074, Val Loss: 1.5455, Val Accuracy: 0.4062 Epoch 1371/10000, Train Loss: 1.5434, Train Accuracy: 0.4029, Val Loss: 1.5454, Val Accuracy: 0.4062 Epoch 1372/10000, Train Loss: 1.5425, Train Accuracy: 0.4029, Val Loss: 1.5452, Val Accuracy: 0.4062 Epoch 1373/10000, Train Loss: 1.5418, Train Accuracy: 0.4040, Val Loss: 1.5451, Val Accuracy: 0.4062 Epoch 1374/10000, Train Loss: 1.5413, Train Accuracy: 0.3917, Val Loss: 1.5450, Val Accuracy: 0.4062 Epoch 1375/10000, Train Loss: 1.5417, Train Accuracy: 0.4185, Val Loss: 1.5448, Val Accuracy: 0.4062 Epoch 1376/10000, Train Loss: 1.5427, Train Accuracy: 0.3940, Val Loss: 1.5447, Val Accuracy: 0.4062 Epoch 1377/10000, Train Loss: 1.5427, Train Accuracy: 0.4107, Val Loss: 1.5445, Val Accuracy: 0.4062 Epoch 1378/10000, Train Loss: 1.5424, Train Accuracy: 0.4007, Val Loss: 1.5444, Val Accuracy: 0.4062 Epoch 1379/10000, Train Loss: 1.5438, Train Accuracy: 0.4029, Val Loss: 1.5443, Val Accuracy: 0.4062 Epoch 1380/10000, Train Loss: 1.5386, Train Accuracy: 0.4141, Val Loss: 1.5441, Val Accuracy: 0.4062 Epoch 1381/10000, Train Loss: 1.5430, Train Accuracy: 0.4029, Val Loss: 1.5440, Val Accuracy: 0.4018 Epoch 1382/10000, Train Loss: 1.5423, Train Accuracy: 0.4174, Val Loss: 1.5438, Val Accuracy: 0.4018 Epoch 1383/10000, Train Loss: 1.5388, Train Accuracy: 0.4241, Val Loss: 1.5437, Val Accuracy: 0.4018 Epoch 1384/10000, Train Loss: 1.5417, Train Accuracy: 0.4018, Val Loss: 1.5435, Val Accuracy: 0.4018 Epoch 1385/10000, Train Loss: 1.5405, Train Accuracy: 0.4062, Val Loss: 1.5434, Val Accuracy: 0.4018 Epoch 1386/10000, Train Loss: 1.5441, Train Accuracy: 0.3984, Val Loss: 1.5432, Val Accuracy: 0.4018 Epoch 1387/10000, Train Loss: 1.5417, Train Accuracy: 0.4018, Val Loss: 1.5431, Val Accuracy: 0.4018 Epoch 1388/10000, Train Loss: 1.5405, Train Accuracy: 0.4107, Val Loss: 1.5429, Val Accuracy: 0.4018 Epoch 1389/10000, Train Loss: 1.5417, Train Accuracy: 0.4074, Val Loss: 1.5428, Val Accuracy: 0.4018 Epoch 1390/10000, Train Loss: 1.5406, Train Accuracy: 0.4040, Val Loss: 1.5426, Val Accuracy: 0.4018 Epoch 1391/10000, Train Loss: 1.5386, Train Accuracy: 0.4085, Val Loss: 1.5424, Val Accuracy: 0.4018 Epoch 1392/10000, Train Loss: 1.5385, Train Accuracy: 0.4074, Val Loss: 1.5423, Val Accuracy: 0.4018 Epoch 1393/10000, Train Loss: 1.5399, Train Accuracy: 0.4085, Val Loss: 1.5421, Val Accuracy: 0.4018 Epoch 1394/10000, Train Loss: 1.5395, Train Accuracy: 0.4007, Val Loss: 1.5420, Val Accuracy: 0.3973 Epoch 1395/10000, Train Loss: 1.5392, Train Accuracy: 0.4007, Val Loss: 1.5419, Val Accuracy: 0.4062 Epoch 1396/10000, Train Loss: 1.5406, Train Accuracy: 0.3895, Val Loss: 1.5417, Val Accuracy: 0.4062 Epoch 1397/10000, Train Loss: 1.5428, Train Accuracy: 0.3929, Val Loss: 1.5415, Val Accuracy: 0.4062 Epoch 1398/10000, Train Loss: 1.5403, Train Accuracy: 0.3940, Val Loss: 1.5414, Val Accuracy: 0.4062 Epoch 1399/10000, Train Loss: 1.5382, Train Accuracy: 0.3984, Val Loss: 1.5412, Val Accuracy: 0.4062 Epoch 1400/10000, Train Loss: 1.5413, Train Accuracy: 0.3895, Val Loss: 1.5410, Val Accuracy: 0.4018 Epoch 1401/10000, Train Loss: 1.5372, Train Accuracy: 0.4018, Val Loss: 1.5409, Val Accuracy: 0.4018 Epoch 1402/10000, Train Loss: 1.5393, Train Accuracy: 0.4074, Val Loss: 1.5407, Val Accuracy: 0.4018 Epoch 1403/10000, Train Loss: 1.5390, Train Accuracy: 0.4029, Val Loss: 1.5406, Val Accuracy: 0.4018 Epoch 1404/10000, Train Loss: 1.5357, Train Accuracy: 0.4051, Val Loss: 1.5404, Val Accuracy: 0.4018 Epoch 1405/10000, Train Loss: 1.5400, Train Accuracy: 0.4118, Val Loss: 1.5403, Val Accuracy: 0.4018 Epoch 1406/10000, Train Loss: 1.5365, Train Accuracy: 0.4129, Val Loss: 1.5402, Val Accuracy: 0.4018 Epoch 1407/10000, Train Loss: 1.5368, Train Accuracy: 0.4029, Val Loss: 1.5400, Val Accuracy: 0.4018 Epoch 1408/10000, Train Loss: 1.5387, Train Accuracy: 0.3839, Val Loss: 1.5399, Val Accuracy: 0.4062 Epoch 1409/10000, Train Loss: 1.5378, Train Accuracy: 0.4118, Val Loss: 1.5398, Val Accuracy: 0.4062 Epoch 1410/10000, Train Loss: 1.5330, Train Accuracy: 0.4118, Val Loss: 1.5396, Val Accuracy: 0.4062 Epoch 1411/10000, Train Loss: 1.5374, Train Accuracy: 0.4163, Val Loss: 1.5394, Val Accuracy: 0.4062 Epoch 1412/10000, Train Loss: 1.5370, Train Accuracy: 0.4185, Val Loss: 1.5393, Val Accuracy: 0.4062 Epoch 1413/10000, Train Loss: 1.5400, Train Accuracy: 0.4062, Val Loss: 1.5391, Val Accuracy: 0.4062 Epoch 1414/10000, Train Loss: 1.5401, Train Accuracy: 0.4018, Val Loss: 1.5390, Val Accuracy: 0.4062 Epoch 1415/10000, Train Loss: 1.5353, Train Accuracy: 0.4118, Val Loss: 1.5388, Val Accuracy: 0.4062 Epoch 1416/10000, Train Loss: 1.5361, Train Accuracy: 0.4085, Val Loss: 1.5386, Val Accuracy: 0.4062 Epoch 1417/10000, Train Loss: 1.5336, Train Accuracy: 0.4018, Val Loss: 1.5385, Val Accuracy: 0.4062 Epoch 1418/10000, Train Loss: 1.5393, Train Accuracy: 0.3873, Val Loss: 1.5383, Val Accuracy: 0.4107 Epoch 1419/10000, Train Loss: 1.5368, Train Accuracy: 0.4051, Val Loss: 1.5382, Val Accuracy: 0.4107 Epoch 1420/10000, Train Loss: 1.5341, Train Accuracy: 0.4018, Val Loss: 1.5380, Val Accuracy: 0.4107 Epoch 1421/10000, Train Loss: 1.5383, Train Accuracy: 0.3951, Val Loss: 1.5379, Val Accuracy: 0.4107 Epoch 1422/10000, Train Loss: 1.5380, Train Accuracy: 0.4096, Val Loss: 1.5377, Val Accuracy: 0.4062 Epoch 1423/10000, Train Loss: 1.5375, Train Accuracy: 0.4129, Val Loss: 1.5375, Val Accuracy: 0.4062 Epoch 1424/10000, Train Loss: 1.5343, Train Accuracy: 0.3951, Val Loss: 1.5374, Val Accuracy: 0.4062 Epoch 1425/10000, Train Loss: 1.5371, Train Accuracy: 0.4330, Val Loss: 1.5372, Val Accuracy: 0.4062 Epoch 1426/10000, Train Loss: 1.5354, Train Accuracy: 0.3895, Val Loss: 1.5371, Val Accuracy: 0.4062 Epoch 1427/10000, Train Loss: 1.5388, Train Accuracy: 0.3962, Val Loss: 1.5369, Val Accuracy: 0.4062 Epoch 1428/10000, Train Loss: 1.5372, Train Accuracy: 0.4129, Val Loss: 1.5368, Val Accuracy: 0.4062 Epoch 1429/10000, Train Loss: 1.5313, Train Accuracy: 0.4208, Val Loss: 1.5366, Val Accuracy: 0.4062 Epoch 1430/10000, Train Loss: 1.5352, Train Accuracy: 0.4241, Val Loss: 1.5365, Val Accuracy: 0.4062 Epoch 1431/10000, Train Loss: 1.5361, Train Accuracy: 0.4040, Val Loss: 1.5363, Val Accuracy: 0.4062 Epoch 1432/10000, Train Loss: 1.5346, Train Accuracy: 0.4252, Val Loss: 1.5361, Val Accuracy: 0.4062 Epoch 1433/10000, Train Loss: 1.5338, Train Accuracy: 0.4230, Val Loss: 1.5360, Val Accuracy: 0.4062 Epoch 1434/10000, Train Loss: 1.5357, Train Accuracy: 0.4029, Val Loss: 1.5358, Val Accuracy: 0.4062 Epoch 1435/10000, Train Loss: 1.5340, Train Accuracy: 0.3984, Val Loss: 1.5357, Val Accuracy: 0.4062 Epoch 1436/10000, Train Loss: 1.5350, Train Accuracy: 0.4129, Val Loss: 1.5356, Val Accuracy: 0.4062 Epoch 1437/10000, Train Loss: 1.5354, Train Accuracy: 0.3940, Val Loss: 1.5354, Val Accuracy: 0.4062 Epoch 1438/10000, Train Loss: 1.5337, Train Accuracy: 0.4107, Val Loss: 1.5353, Val Accuracy: 0.4062 Epoch 1439/10000, Train Loss: 1.5327, Train Accuracy: 0.4018, Val Loss: 1.5352, Val Accuracy: 0.4062 Epoch 1440/10000, Train Loss: 1.5346, Train Accuracy: 0.4018, Val Loss: 1.5350, Val Accuracy: 0.4062 Epoch 1441/10000, Train Loss: 1.5341, Train Accuracy: 0.4141, Val Loss: 1.5349, Val Accuracy: 0.4062 Epoch 1442/10000, Train Loss: 1.5298, Train Accuracy: 0.4163, Val Loss: 1.5347, Val Accuracy: 0.4062 Epoch 1443/10000, Train Loss: 1.5295, Train Accuracy: 0.4062, Val Loss: 1.5345, Val Accuracy: 0.4062 Epoch 1444/10000, Train Loss: 1.5324, Train Accuracy: 0.4219, Val Loss: 1.5344, Val Accuracy: 0.4062 Epoch 1445/10000, Train Loss: 1.5313, Train Accuracy: 0.4230, Val Loss: 1.5343, Val Accuracy: 0.4062 Epoch 1446/10000, Train Loss: 1.5331, Train Accuracy: 0.4029, Val Loss: 1.5341, Val Accuracy: 0.4062 Epoch 1447/10000, Train Loss: 1.5330, Train Accuracy: 0.4141, Val Loss: 1.5339, Val Accuracy: 0.4062 Epoch 1448/10000, Train Loss: 1.5337, Train Accuracy: 0.4141, Val Loss: 1.5337, Val Accuracy: 0.4062 Epoch 1449/10000, Train Loss: 1.5297, Train Accuracy: 0.4029, Val Loss: 1.5335, Val Accuracy: 0.4062 Epoch 1450/10000, Train Loss: 1.5293, Train Accuracy: 0.4319, Val Loss: 1.5334, Val Accuracy: 0.4062 Epoch 1451/10000, Train Loss: 1.5295, Train Accuracy: 0.4051, Val Loss: 1.5332, Val Accuracy: 0.4062 Epoch 1452/10000, Train Loss: 1.5308, Train Accuracy: 0.4163, Val Loss: 1.5330, Val Accuracy: 0.4107 Epoch 1453/10000, Train Loss: 1.5278, Train Accuracy: 0.4286, Val Loss: 1.5329, Val Accuracy: 0.4107 Epoch 1454/10000, Train Loss: 1.5259, Train Accuracy: 0.4118, Val Loss: 1.5327, Val Accuracy: 0.4107 Epoch 1455/10000, Train Loss: 1.5296, Train Accuracy: 0.4208, Val Loss: 1.5326, Val Accuracy: 0.4107 Epoch 1456/10000, Train Loss: 1.5308, Train Accuracy: 0.4241, Val Loss: 1.5324, Val Accuracy: 0.4152 Epoch 1457/10000, Train Loss: 1.5300, Train Accuracy: 0.4185, Val Loss: 1.5322, Val Accuracy: 0.4152 Epoch 1458/10000, Train Loss: 1.5303, Train Accuracy: 0.4118, Val Loss: 1.5321, Val Accuracy: 0.4196 Epoch 1459/10000, Train Loss: 1.5270, Train Accuracy: 0.4353, Val Loss: 1.5319, Val Accuracy: 0.4152 Epoch 1460/10000, Train Loss: 1.5315, Train Accuracy: 0.4208, Val Loss: 1.5318, Val Accuracy: 0.4196 Epoch 1461/10000, Train Loss: 1.5307, Train Accuracy: 0.4152, Val Loss: 1.5316, Val Accuracy: 0.4196 Epoch 1462/10000, Train Loss: 1.5274, Train Accuracy: 0.4185, Val Loss: 1.5314, Val Accuracy: 0.4196 Epoch 1463/10000, Train Loss: 1.5279, Train Accuracy: 0.4219, Val Loss: 1.5313, Val Accuracy: 0.4241 Epoch 1464/10000, Train Loss: 1.5272, Train Accuracy: 0.4040, Val Loss: 1.5311, Val Accuracy: 0.4241 Epoch 1465/10000, Train Loss: 1.5335, Train Accuracy: 0.4007, Val Loss: 1.5309, Val Accuracy: 0.4241 Epoch 1466/10000, Train Loss: 1.5297, Train Accuracy: 0.4275, Val Loss: 1.5308, Val Accuracy: 0.4241 Epoch 1467/10000, Train Loss: 1.5292, Train Accuracy: 0.4007, Val Loss: 1.5306, Val Accuracy: 0.4241 Epoch 1468/10000, Train Loss: 1.5274, Train Accuracy: 0.4275, Val Loss: 1.5304, Val Accuracy: 0.4241 Epoch 1469/10000, Train Loss: 1.5257, Train Accuracy: 0.4074, Val Loss: 1.5303, Val Accuracy: 0.4241 Epoch 1470/10000, Train Loss: 1.5302, Train Accuracy: 0.4107, Val Loss: 1.5302, Val Accuracy: 0.4241 Epoch 1471/10000, Train Loss: 1.5287, Train Accuracy: 0.4107, Val Loss: 1.5301, Val Accuracy: 0.4241 Epoch 1472/10000, Train Loss: 1.5284, Train Accuracy: 0.4219, Val Loss: 1.5299, Val Accuracy: 0.4241 Epoch 1473/10000, Train Loss: 1.5320, Train Accuracy: 0.3951, Val Loss: 1.5298, Val Accuracy: 0.4241 Epoch 1474/10000, Train Loss: 1.5279, Train Accuracy: 0.4163, Val Loss: 1.5296, Val Accuracy: 0.4241 Epoch 1475/10000, Train Loss: 1.5282, Train Accuracy: 0.4185, Val Loss: 1.5294, Val Accuracy: 0.4241 Epoch 1476/10000, Train Loss: 1.5272, Train Accuracy: 0.4163, Val Loss: 1.5293, Val Accuracy: 0.4241 Epoch 1477/10000, Train Loss: 1.5266, Train Accuracy: 0.4275, Val Loss: 1.5292, Val Accuracy: 0.4241 Epoch 1478/10000, Train Loss: 1.5251, Train Accuracy: 0.4118, Val Loss: 1.5290, Val Accuracy: 0.4241 Epoch 1479/10000, Train Loss: 1.5272, Train Accuracy: 0.4051, Val Loss: 1.5288, Val Accuracy: 0.4241 Epoch 1480/10000, Train Loss: 1.5278, Train Accuracy: 0.4085, Val Loss: 1.5286, Val Accuracy: 0.4241 Epoch 1481/10000, Train Loss: 1.5272, Train Accuracy: 0.4029, Val Loss: 1.5285, Val Accuracy: 0.4241 Epoch 1482/10000, Train Loss: 1.5235, Train Accuracy: 0.4196, Val Loss: 1.5283, Val Accuracy: 0.4286 Epoch 1483/10000, Train Loss: 1.5247, Train Accuracy: 0.4051, Val Loss: 1.5281, Val Accuracy: 0.4241 Epoch 1484/10000, Train Loss: 1.5247, Train Accuracy: 0.4163, Val Loss: 1.5280, Val Accuracy: 0.4286 Epoch 1485/10000, Train Loss: 1.5255, Train Accuracy: 0.3951, Val Loss: 1.5278, Val Accuracy: 0.4286 Epoch 1486/10000, Train Loss: 1.5225, Train Accuracy: 0.4018, Val Loss: 1.5276, Val Accuracy: 0.4286 Epoch 1487/10000, Train Loss: 1.5235, Train Accuracy: 0.4263, Val Loss: 1.5275, Val Accuracy: 0.4286 Epoch 1488/10000, Train Loss: 1.5204, Train Accuracy: 0.4319, Val Loss: 1.5273, Val Accuracy: 0.4286 Epoch 1489/10000, Train Loss: 1.5253, Train Accuracy: 0.4085, Val Loss: 1.5272, Val Accuracy: 0.4286 Epoch 1490/10000, Train Loss: 1.5271, Train Accuracy: 0.3984, Val Loss: 1.5270, Val Accuracy: 0.4286 Epoch 1491/10000, Train Loss: 1.5228, Train Accuracy: 0.4152, Val Loss: 1.5269, Val Accuracy: 0.4286 Epoch 1492/10000, Train Loss: 1.5273, Train Accuracy: 0.4085, Val Loss: 1.5267, Val Accuracy: 0.4286 Epoch 1493/10000, Train Loss: 1.5277, Train Accuracy: 0.4029, Val Loss: 1.5266, Val Accuracy: 0.4286 Epoch 1494/10000, Train Loss: 1.5227, Train Accuracy: 0.4185, Val Loss: 1.5264, Val Accuracy: 0.4286 Epoch 1495/10000, Train Loss: 1.5263, Train Accuracy: 0.4196, Val Loss: 1.5262, Val Accuracy: 0.4330 Epoch 1496/10000, Train Loss: 1.5247, Train Accuracy: 0.4275, Val Loss: 1.5260, Val Accuracy: 0.4330 Epoch 1497/10000, Train Loss: 1.5252, Train Accuracy: 0.4107, Val Loss: 1.5259, Val Accuracy: 0.4330 Epoch 1498/10000, Train Loss: 1.5246, Train Accuracy: 0.4319, Val Loss: 1.5258, Val Accuracy: 0.4330 Epoch 1499/10000, Train Loss: 1.5239, Train Accuracy: 0.4129, Val Loss: 1.5256, Val Accuracy: 0.4330 Epoch 1500/10000, Train Loss: 1.5193, Train Accuracy: 0.4241, Val Loss: 1.5254, Val Accuracy: 0.4330 Epoch 1501/10000, Train Loss: 1.5223, Train Accuracy: 0.4118, Val Loss: 1.5252, Val Accuracy: 0.4330 Epoch 1502/10000, Train Loss: 1.5247, Train Accuracy: 0.4219, Val Loss: 1.5250, Val Accuracy: 0.4330 Epoch 1503/10000, Train Loss: 1.5222, Train Accuracy: 0.4051, Val Loss: 1.5249, Val Accuracy: 0.4330 Epoch 1504/10000, Train Loss: 1.5239, Train Accuracy: 0.3973, Val Loss: 1.5247, Val Accuracy: 0.4330 Epoch 1505/10000, Train Loss: 1.5204, Train Accuracy: 0.4342, Val Loss: 1.5245, Val Accuracy: 0.4330 Epoch 1506/10000, Train Loss: 1.5182, Train Accuracy: 0.4364, Val Loss: 1.5244, Val Accuracy: 0.4330 Epoch 1507/10000, Train Loss: 1.5229, Train Accuracy: 0.4107, Val Loss: 1.5242, Val Accuracy: 0.4330 Epoch 1508/10000, Train Loss: 1.5216, Train Accuracy: 0.4208, Val Loss: 1.5241, Val Accuracy: 0.4330 Epoch 1509/10000, Train Loss: 1.5222, Train Accuracy: 0.4208, Val Loss: 1.5239, Val Accuracy: 0.4330 Epoch 1510/10000, Train Loss: 1.5232, Train Accuracy: 0.4096, Val Loss: 1.5238, Val Accuracy: 0.4330 Epoch 1511/10000, Train Loss: 1.5249, Train Accuracy: 0.4040, Val Loss: 1.5235, Val Accuracy: 0.4330 Epoch 1512/10000, Train Loss: 1.5184, Train Accuracy: 0.4040, Val Loss: 1.5234, Val Accuracy: 0.4330 Epoch 1513/10000, Train Loss: 1.5214, Train Accuracy: 0.4297, Val Loss: 1.5232, Val Accuracy: 0.4330 Epoch 1514/10000, Train Loss: 1.5223, Train Accuracy: 0.4141, Val Loss: 1.5230, Val Accuracy: 0.4330 Epoch 1515/10000, Train Loss: 1.5216, Train Accuracy: 0.4219, Val Loss: 1.5229, Val Accuracy: 0.4330 Epoch 1516/10000, Train Loss: 1.5214, Train Accuracy: 0.4118, Val Loss: 1.5228, Val Accuracy: 0.4330 Epoch 1517/10000, Train Loss: 1.5166, Train Accuracy: 0.4263, Val Loss: 1.5227, Val Accuracy: 0.4330 Epoch 1518/10000, Train Loss: 1.5202, Train Accuracy: 0.4096, Val Loss: 1.5225, Val Accuracy: 0.4330 Epoch 1519/10000, Train Loss: 1.5191, Train Accuracy: 0.3984, Val Loss: 1.5224, Val Accuracy: 0.4330 Epoch 1520/10000, Train Loss: 1.5219, Train Accuracy: 0.4174, Val Loss: 1.5222, Val Accuracy: 0.4330 Epoch 1521/10000, Train Loss: 1.5236, Train Accuracy: 0.4330, Val Loss: 1.5220, Val Accuracy: 0.4330 Epoch 1522/10000, Train Loss: 1.5202, Train Accuracy: 0.4297, Val Loss: 1.5219, Val Accuracy: 0.4330 Epoch 1523/10000, Train Loss: 1.5223, Train Accuracy: 0.4174, Val Loss: 1.5217, Val Accuracy: 0.4330 Epoch 1524/10000, Train Loss: 1.5213, Train Accuracy: 0.4141, Val Loss: 1.5215, Val Accuracy: 0.4330 Epoch 1525/10000, Train Loss: 1.5179, Train Accuracy: 0.4085, Val Loss: 1.5214, Val Accuracy: 0.4330 Epoch 1526/10000, Train Loss: 1.5184, Train Accuracy: 0.4353, Val Loss: 1.5212, Val Accuracy: 0.4330 Epoch 1527/10000, Train Loss: 1.5199, Train Accuracy: 0.4263, Val Loss: 1.5210, Val Accuracy: 0.4330 Epoch 1528/10000, Train Loss: 1.5177, Train Accuracy: 0.4219, Val Loss: 1.5209, Val Accuracy: 0.4330 Epoch 1529/10000, Train Loss: 1.5222, Train Accuracy: 0.4096, Val Loss: 1.5207, Val Accuracy: 0.4330 Epoch 1530/10000, Train Loss: 1.5183, Train Accuracy: 0.4196, Val Loss: 1.5205, Val Accuracy: 0.4330 Epoch 1531/10000, Train Loss: 1.5167, Train Accuracy: 0.4386, Val Loss: 1.5204, Val Accuracy: 0.4330 Epoch 1532/10000, Train Loss: 1.5160, Train Accuracy: 0.4129, Val Loss: 1.5202, Val Accuracy: 0.4330 Epoch 1533/10000, Train Loss: 1.5196, Train Accuracy: 0.4074, Val Loss: 1.5201, Val Accuracy: 0.4330 Epoch 1534/10000, Train Loss: 1.5151, Train Accuracy: 0.4118, Val Loss: 1.5199, Val Accuracy: 0.4330 Epoch 1535/10000, Train Loss: 1.5155, Train Accuracy: 0.4219, Val Loss: 1.5197, Val Accuracy: 0.4375 Epoch 1536/10000, Train Loss: 1.5146, Train Accuracy: 0.4141, Val Loss: 1.5195, Val Accuracy: 0.4375 Epoch 1537/10000, Train Loss: 1.5197, Train Accuracy: 0.4397, Val Loss: 1.5194, Val Accuracy: 0.4375 Epoch 1538/10000, Train Loss: 1.5196, Train Accuracy: 0.4141, Val Loss: 1.5192, Val Accuracy: 0.4375 Epoch 1539/10000, Train Loss: 1.5132, Train Accuracy: 0.4286, Val Loss: 1.5191, Val Accuracy: 0.4375 Epoch 1540/10000, Train Loss: 1.5193, Train Accuracy: 0.4208, Val Loss: 1.5189, Val Accuracy: 0.4375 Epoch 1541/10000, Train Loss: 1.5154, Train Accuracy: 0.4152, Val Loss: 1.5187, Val Accuracy: 0.4375 Epoch 1542/10000, Train Loss: 1.5160, Train Accuracy: 0.4174, Val Loss: 1.5186, Val Accuracy: 0.4375 Epoch 1543/10000, Train Loss: 1.5175, Train Accuracy: 0.4241, Val Loss: 1.5184, Val Accuracy: 0.4375 Epoch 1544/10000, Train Loss: 1.5126, Train Accuracy: 0.4464, Val Loss: 1.5183, Val Accuracy: 0.4375 Epoch 1545/10000, Train Loss: 1.5128, Train Accuracy: 0.4330, Val Loss: 1.5181, Val Accuracy: 0.4375 Epoch 1546/10000, Train Loss: 1.5155, Train Accuracy: 0.4051, Val Loss: 1.5179, Val Accuracy: 0.4375 Epoch 1547/10000, Train Loss: 1.5147, Train Accuracy: 0.4230, Val Loss: 1.5178, Val Accuracy: 0.4330 Epoch 1548/10000, Train Loss: 1.5149, Train Accuracy: 0.4152, Val Loss: 1.5176, Val Accuracy: 0.4330 Epoch 1549/10000, Train Loss: 1.5152, Train Accuracy: 0.4163, Val Loss: 1.5174, Val Accuracy: 0.4286 Epoch 1550/10000, Train Loss: 1.5169, Train Accuracy: 0.4230, Val Loss: 1.5173, Val Accuracy: 0.4286 Epoch 1551/10000, Train Loss: 1.5170, Train Accuracy: 0.4196, Val Loss: 1.5171, Val Accuracy: 0.4286 Epoch 1552/10000, Train Loss: 1.5164, Train Accuracy: 0.4185, Val Loss: 1.5170, Val Accuracy: 0.4286 Epoch 1553/10000, Train Loss: 1.5137, Train Accuracy: 0.4208, Val Loss: 1.5168, Val Accuracy: 0.4286 Epoch 1554/10000, Train Loss: 1.5116, Train Accuracy: 0.4263, Val Loss: 1.5167, Val Accuracy: 0.4286 Epoch 1555/10000, Train Loss: 1.5178, Train Accuracy: 0.4118, Val Loss: 1.5165, Val Accuracy: 0.4286 Epoch 1556/10000, Train Loss: 1.5180, Train Accuracy: 0.4152, Val Loss: 1.5163, Val Accuracy: 0.4286 Epoch 1557/10000, Train Loss: 1.5098, Train Accuracy: 0.4475, Val Loss: 1.5162, Val Accuracy: 0.4241 Epoch 1558/10000, Train Loss: 1.5172, Train Accuracy: 0.4208, Val Loss: 1.5160, Val Accuracy: 0.4241 Epoch 1559/10000, Train Loss: 1.5178, Train Accuracy: 0.4219, Val Loss: 1.5158, Val Accuracy: 0.4241 Epoch 1560/10000, Train Loss: 1.5076, Train Accuracy: 0.4375, Val Loss: 1.5157, Val Accuracy: 0.4286 Epoch 1561/10000, Train Loss: 1.5112, Train Accuracy: 0.4241, Val Loss: 1.5155, Val Accuracy: 0.4330 Epoch 1562/10000, Train Loss: 1.5158, Train Accuracy: 0.4185, Val Loss: 1.5154, Val Accuracy: 0.4286 Epoch 1563/10000, Train Loss: 1.5120, Train Accuracy: 0.4297, Val Loss: 1.5152, Val Accuracy: 0.4286 Epoch 1564/10000, Train Loss: 1.5138, Train Accuracy: 0.4018, Val Loss: 1.5150, Val Accuracy: 0.4330 Epoch 1565/10000, Train Loss: 1.5099, Train Accuracy: 0.4386, Val Loss: 1.5149, Val Accuracy: 0.4330 Epoch 1566/10000, Train Loss: 1.5123, Train Accuracy: 0.4185, Val Loss: 1.5147, Val Accuracy: 0.4286 Epoch 1567/10000, Train Loss: 1.5144, Train Accuracy: 0.4062, Val Loss: 1.5146, Val Accuracy: 0.4286 Epoch 1568/10000, Train Loss: 1.5126, Train Accuracy: 0.4464, Val Loss: 1.5144, Val Accuracy: 0.4286 Epoch 1569/10000, Train Loss: 1.5177, Train Accuracy: 0.4219, Val Loss: 1.5142, Val Accuracy: 0.4286 Epoch 1570/10000, Train Loss: 1.5115, Train Accuracy: 0.4118, Val Loss: 1.5140, Val Accuracy: 0.4286 Epoch 1571/10000, Train Loss: 1.5111, Train Accuracy: 0.4330, Val Loss: 1.5138, Val Accuracy: 0.4286 Epoch 1572/10000, Train Loss: 1.5138, Train Accuracy: 0.4230, Val Loss: 1.5137, Val Accuracy: 0.4286 Epoch 1573/10000, Train Loss: 1.5159, Train Accuracy: 0.4018, Val Loss: 1.5135, Val Accuracy: 0.4286 Epoch 1574/10000, Train Loss: 1.5110, Train Accuracy: 0.4230, Val Loss: 1.5134, Val Accuracy: 0.4286 Epoch 1575/10000, Train Loss: 1.5096, Train Accuracy: 0.4297, Val Loss: 1.5132, Val Accuracy: 0.4286 Epoch 1576/10000, Train Loss: 1.5104, Train Accuracy: 0.4129, Val Loss: 1.5131, Val Accuracy: 0.4286 Epoch 1577/10000, Train Loss: 1.5078, Train Accuracy: 0.4174, Val Loss: 1.5129, Val Accuracy: 0.4286 Epoch 1578/10000, Train Loss: 1.5142, Train Accuracy: 0.4141, Val Loss: 1.5128, Val Accuracy: 0.4286 Epoch 1579/10000, Train Loss: 1.5132, Train Accuracy: 0.4062, Val Loss: 1.5127, Val Accuracy: 0.4286 Epoch 1580/10000, Train Loss: 1.5083, Train Accuracy: 0.4364, Val Loss: 1.5125, Val Accuracy: 0.4286 Epoch 1581/10000, Train Loss: 1.5057, Train Accuracy: 0.4431, Val Loss: 1.5124, Val Accuracy: 0.4286 Epoch 1582/10000, Train Loss: 1.5128, Train Accuracy: 0.4275, Val Loss: 1.5123, Val Accuracy: 0.4286 Epoch 1583/10000, Train Loss: 1.5104, Train Accuracy: 0.4152, Val Loss: 1.5121, Val Accuracy: 0.4286 Epoch 1584/10000, Train Loss: 1.5061, Train Accuracy: 0.4420, Val Loss: 1.5119, Val Accuracy: 0.4286 Epoch 1585/10000, Train Loss: 1.5109, Train Accuracy: 0.4196, Val Loss: 1.5117, Val Accuracy: 0.4286 Epoch 1586/10000, Train Loss: 1.5081, Train Accuracy: 0.4330, Val Loss: 1.5115, Val Accuracy: 0.4286 Epoch 1587/10000, Train Loss: 1.5089, Train Accuracy: 0.4330, Val Loss: 1.5113, Val Accuracy: 0.4286 Epoch 1588/10000, Train Loss: 1.5144, Train Accuracy: 0.4219, Val Loss: 1.5111, Val Accuracy: 0.4286 Epoch 1589/10000, Train Loss: 1.5077, Train Accuracy: 0.4219, Val Loss: 1.5110, Val Accuracy: 0.4286 Epoch 1590/10000, Train Loss: 1.5084, Train Accuracy: 0.4208, Val Loss: 1.5109, Val Accuracy: 0.4286 Epoch 1591/10000, Train Loss: 1.5062, Train Accuracy: 0.4408, Val Loss: 1.5107, Val Accuracy: 0.4286 Epoch 1592/10000, Train Loss: 1.5084, Train Accuracy: 0.4252, Val Loss: 1.5106, Val Accuracy: 0.4286 Epoch 1593/10000, Train Loss: 1.5099, Train Accuracy: 0.4286, Val Loss: 1.5104, Val Accuracy: 0.4286 Epoch 1594/10000, Train Loss: 1.5087, Train Accuracy: 0.4275, Val Loss: 1.5102, Val Accuracy: 0.4286 Epoch 1595/10000, Train Loss: 1.5046, Train Accuracy: 0.4364, Val Loss: 1.5100, Val Accuracy: 0.4330 Epoch 1596/10000, Train Loss: 1.5087, Train Accuracy: 0.4275, Val Loss: 1.5099, Val Accuracy: 0.4330 Epoch 1597/10000, Train Loss: 1.5092, Train Accuracy: 0.4107, Val Loss: 1.5097, Val Accuracy: 0.4375 Epoch 1598/10000, Train Loss: 1.5100, Train Accuracy: 0.4330, Val Loss: 1.5095, Val Accuracy: 0.4375 Epoch 1599/10000, Train Loss: 1.5046, Train Accuracy: 0.4319, Val Loss: 1.5094, Val Accuracy: 0.4375 Epoch 1600/10000, Train Loss: 1.5037, Train Accuracy: 0.4330, Val Loss: 1.5092, Val Accuracy: 0.4330 Epoch 1601/10000, Train Loss: 1.5084, Train Accuracy: 0.4263, Val Loss: 1.5090, Val Accuracy: 0.4330 Epoch 1602/10000, Train Loss: 1.5017, Train Accuracy: 0.4420, Val Loss: 1.5089, Val Accuracy: 0.4330 Epoch 1603/10000, Train Loss: 1.5071, Train Accuracy: 0.4029, Val Loss: 1.5087, Val Accuracy: 0.4330 Epoch 1604/10000, Train Loss: 1.5114, Train Accuracy: 0.4163, Val Loss: 1.5086, Val Accuracy: 0.4375 Epoch 1605/10000, Train Loss: 1.5073, Train Accuracy: 0.4107, Val Loss: 1.5084, Val Accuracy: 0.4375 Epoch 1606/10000, Train Loss: 1.5012, Train Accuracy: 0.4275, Val Loss: 1.5083, Val Accuracy: 0.4330 Epoch 1607/10000, Train Loss: 1.5051, Train Accuracy: 0.4275, Val Loss: 1.5081, Val Accuracy: 0.4330 Epoch 1608/10000, Train Loss: 1.5089, Train Accuracy: 0.4386, Val Loss: 1.5079, Val Accuracy: 0.4330 Epoch 1609/10000, Train Loss: 1.5088, Train Accuracy: 0.4096, Val Loss: 1.5077, Val Accuracy: 0.4330 Epoch 1610/10000, Train Loss: 1.5024, Train Accuracy: 0.4286, Val Loss: 1.5076, Val Accuracy: 0.4330 Epoch 1611/10000, Train Loss: 1.5030, Train Accuracy: 0.4464, Val Loss: 1.5075, Val Accuracy: 0.4330 Epoch 1612/10000, Train Loss: 1.5071, Train Accuracy: 0.4342, Val Loss: 1.5073, Val Accuracy: 0.4375 Epoch 1613/10000, Train Loss: 1.5067, Train Accuracy: 0.4420, Val Loss: 1.5072, Val Accuracy: 0.4420 Epoch 1614/10000, Train Loss: 1.5048, Train Accuracy: 0.4364, Val Loss: 1.5070, Val Accuracy: 0.4420 Epoch 1615/10000, Train Loss: 1.5014, Train Accuracy: 0.4286, Val Loss: 1.5068, Val Accuracy: 0.4420 Epoch 1616/10000, Train Loss: 1.5040, Train Accuracy: 0.4196, Val Loss: 1.5066, Val Accuracy: 0.4464 Epoch 1617/10000, Train Loss: 1.5048, Train Accuracy: 0.4297, Val Loss: 1.5065, Val Accuracy: 0.4464 Epoch 1618/10000, Train Loss: 1.5064, Train Accuracy: 0.4375, Val Loss: 1.5063, Val Accuracy: 0.4464 Epoch 1619/10000, Train Loss: 1.5031, Train Accuracy: 0.4342, Val Loss: 1.5061, Val Accuracy: 0.4509 Epoch 1620/10000, Train Loss: 1.5023, Train Accuracy: 0.4397, Val Loss: 1.5060, Val Accuracy: 0.4509 Epoch 1621/10000, Train Loss: 1.5019, Train Accuracy: 0.4408, Val Loss: 1.5058, Val Accuracy: 0.4509 Epoch 1622/10000, Train Loss: 1.5004, Train Accuracy: 0.4509, Val Loss: 1.5056, Val Accuracy: 0.4509 Epoch 1623/10000, Train Loss: 1.5028, Train Accuracy: 0.4196, Val Loss: 1.5055, Val Accuracy: 0.4509 Epoch 1624/10000, Train Loss: 1.5037, Train Accuracy: 0.4408, Val Loss: 1.5053, Val Accuracy: 0.4509 Epoch 1625/10000, Train Loss: 1.5056, Train Accuracy: 0.4163, Val Loss: 1.5052, Val Accuracy: 0.4509 Epoch 1626/10000, Train Loss: 1.5014, Train Accuracy: 0.4386, Val Loss: 1.5050, Val Accuracy: 0.4509 Epoch 1627/10000, Train Loss: 1.5087, Train Accuracy: 0.4219, Val Loss: 1.5048, Val Accuracy: 0.4509 Epoch 1628/10000, Train Loss: 1.5035, Train Accuracy: 0.4319, Val Loss: 1.5047, Val Accuracy: 0.4509 Epoch 1629/10000, Train Loss: 1.5044, Train Accuracy: 0.4085, Val Loss: 1.5046, Val Accuracy: 0.4509 Epoch 1630/10000, Train Loss: 1.4992, Train Accuracy: 0.4420, Val Loss: 1.5044, Val Accuracy: 0.4509 Epoch 1631/10000, Train Loss: 1.5036, Train Accuracy: 0.4062, Val Loss: 1.5042, Val Accuracy: 0.4509 Epoch 1632/10000, Train Loss: 1.5034, Train Accuracy: 0.4386, Val Loss: 1.5041, Val Accuracy: 0.4509 Epoch 1633/10000, Train Loss: 1.5086, Train Accuracy: 0.4230, Val Loss: 1.5039, Val Accuracy: 0.4509 Epoch 1634/10000, Train Loss: 1.4967, Train Accuracy: 0.4397, Val Loss: 1.5038, Val Accuracy: 0.4509 Epoch 1635/10000, Train Loss: 1.5059, Train Accuracy: 0.4196, Val Loss: 1.5036, Val Accuracy: 0.4509 Epoch 1636/10000, Train Loss: 1.5021, Train Accuracy: 0.4241, Val Loss: 1.5034, Val Accuracy: 0.4509 Epoch 1637/10000, Train Loss: 1.5029, Train Accuracy: 0.4286, Val Loss: 1.5033, Val Accuracy: 0.4509 Epoch 1638/10000, Train Loss: 1.5006, Train Accuracy: 0.4163, Val Loss: 1.5031, Val Accuracy: 0.4509 Epoch 1639/10000, Train Loss: 1.5005, Train Accuracy: 0.4152, Val Loss: 1.5029, Val Accuracy: 0.4509 Epoch 1640/10000, Train Loss: 1.5031, Train Accuracy: 0.4297, Val Loss: 1.5027, Val Accuracy: 0.4509 Epoch 1641/10000, Train Loss: 1.4989, Train Accuracy: 0.4141, Val Loss: 1.5025, Val Accuracy: 0.4509 Epoch 1642/10000, Train Loss: 1.5005, Train Accuracy: 0.4252, Val Loss: 1.5024, Val Accuracy: 0.4509 Epoch 1643/10000, Train Loss: 1.5007, Train Accuracy: 0.4464, Val Loss: 1.5023, Val Accuracy: 0.4509 Epoch 1644/10000, Train Loss: 1.5052, Train Accuracy: 0.4196, Val Loss: 1.5022, Val Accuracy: 0.4509 Epoch 1645/10000, Train Loss: 1.4995, Train Accuracy: 0.4375, Val Loss: 1.5020, Val Accuracy: 0.4509 Epoch 1646/10000, Train Loss: 1.4979, Train Accuracy: 0.4397, Val Loss: 1.5018, Val Accuracy: 0.4509 Epoch 1647/10000, Train Loss: 1.5019, Train Accuracy: 0.4219, Val Loss: 1.5017, Val Accuracy: 0.4509 Epoch 1648/10000, Train Loss: 1.5015, Train Accuracy: 0.4196, Val Loss: 1.5016, Val Accuracy: 0.4509 Epoch 1649/10000, Train Loss: 1.4988, Train Accuracy: 0.4397, Val Loss: 1.5014, Val Accuracy: 0.4509 Epoch 1650/10000, Train Loss: 1.4989, Train Accuracy: 0.4531, Val Loss: 1.5011, Val Accuracy: 0.4509 Epoch 1651/10000, Train Loss: 1.4964, Train Accuracy: 0.4230, Val Loss: 1.5010, Val Accuracy: 0.4509 Epoch 1652/10000, Train Loss: 1.5004, Train Accuracy: 0.4096, Val Loss: 1.5008, Val Accuracy: 0.4509 Epoch 1653/10000, Train Loss: 1.4967, Train Accuracy: 0.4342, Val Loss: 1.5007, Val Accuracy: 0.4509 Epoch 1654/10000, Train Loss: 1.4964, Train Accuracy: 0.4475, Val Loss: 1.5005, Val Accuracy: 0.4509 Epoch 1655/10000, Train Loss: 1.4968, Train Accuracy: 0.4375, Val Loss: 1.5004, Val Accuracy: 0.4509 Epoch 1656/10000, Train Loss: 1.4998, Train Accuracy: 0.4297, Val Loss: 1.5002, Val Accuracy: 0.4509 Epoch 1657/10000, Train Loss: 1.4966, Train Accuracy: 0.4475, Val Loss: 1.5000, Val Accuracy: 0.4509 Epoch 1658/10000, Train Loss: 1.4963, Train Accuracy: 0.4263, Val Loss: 1.4998, Val Accuracy: 0.4509 Epoch 1659/10000, Train Loss: 1.4985, Train Accuracy: 0.4185, Val Loss: 1.4997, Val Accuracy: 0.4464 Epoch 1660/10000, Train Loss: 1.4990, Train Accuracy: 0.4353, Val Loss: 1.4995, Val Accuracy: 0.4464 Epoch 1661/10000, Train Loss: 1.4972, Train Accuracy: 0.4286, Val Loss: 1.4994, Val Accuracy: 0.4509 Epoch 1662/10000, Train Loss: 1.4939, Train Accuracy: 0.4442, Val Loss: 1.4992, Val Accuracy: 0.4509 Epoch 1663/10000, Train Loss: 1.4956, Train Accuracy: 0.4342, Val Loss: 1.4990, Val Accuracy: 0.4464 Epoch 1664/10000, Train Loss: 1.4955, Train Accuracy: 0.4487, Val Loss: 1.4988, Val Accuracy: 0.4464 Epoch 1665/10000, Train Loss: 1.4977, Train Accuracy: 0.4353, Val Loss: 1.4986, Val Accuracy: 0.4464 Epoch 1666/10000, Train Loss: 1.4963, Train Accuracy: 0.4420, Val Loss: 1.4984, Val Accuracy: 0.4509 Epoch 1667/10000, Train Loss: 1.4944, Train Accuracy: 0.4275, Val Loss: 1.4983, Val Accuracy: 0.4509 Epoch 1668/10000, Train Loss: 1.4951, Train Accuracy: 0.4408, Val Loss: 1.4982, Val Accuracy: 0.4464 Epoch 1669/10000, Train Loss: 1.4973, Train Accuracy: 0.4375, Val Loss: 1.4981, Val Accuracy: 0.4464 Epoch 1670/10000, Train Loss: 1.4960, Train Accuracy: 0.4353, Val Loss: 1.4980, Val Accuracy: 0.4464 Epoch 1671/10000, Train Loss: 1.4970, Train Accuracy: 0.4420, Val Loss: 1.4978, Val Accuracy: 0.4464 Epoch 1672/10000, Train Loss: 1.4976, Train Accuracy: 0.4342, Val Loss: 1.4976, Val Accuracy: 0.4464 Epoch 1673/10000, Train Loss: 1.4931, Train Accuracy: 0.4319, Val Loss: 1.4974, Val Accuracy: 0.4464 Epoch 1674/10000, Train Loss: 1.4974, Train Accuracy: 0.4442, Val Loss: 1.4972, Val Accuracy: 0.4464 Epoch 1675/10000, Train Loss: 1.4936, Train Accuracy: 0.4431, Val Loss: 1.4971, Val Accuracy: 0.4464 Epoch 1676/10000, Train Loss: 1.4967, Train Accuracy: 0.4230, Val Loss: 1.4969, Val Accuracy: 0.4464 Epoch 1677/10000, Train Loss: 1.4968, Train Accuracy: 0.4252, Val Loss: 1.4968, Val Accuracy: 0.4464 Epoch 1678/10000, Train Loss: 1.4956, Train Accuracy: 0.4408, Val Loss: 1.4965, Val Accuracy: 0.4509 Epoch 1679/10000, Train Loss: 1.4932, Train Accuracy: 0.4420, Val Loss: 1.4964, Val Accuracy: 0.4464 Epoch 1680/10000, Train Loss: 1.4933, Train Accuracy: 0.4554, Val Loss: 1.4962, Val Accuracy: 0.4464 Epoch 1681/10000, Train Loss: 1.4965, Train Accuracy: 0.4397, Val Loss: 1.4960, Val Accuracy: 0.4509 Epoch 1682/10000, Train Loss: 1.4927, Train Accuracy: 0.4319, Val Loss: 1.4959, Val Accuracy: 0.4509 Epoch 1683/10000, Train Loss: 1.4961, Train Accuracy: 0.4286, Val Loss: 1.4957, Val Accuracy: 0.4509 Epoch 1684/10000, Train Loss: 1.4914, Train Accuracy: 0.4319, Val Loss: 1.4955, Val Accuracy: 0.4509 Epoch 1685/10000, Train Loss: 1.4963, Train Accuracy: 0.4286, Val Loss: 1.4954, Val Accuracy: 0.4509 Epoch 1686/10000, Train Loss: 1.4903, Train Accuracy: 0.4342, Val Loss: 1.4953, Val Accuracy: 0.4509 Epoch 1687/10000, Train Loss: 1.4892, Train Accuracy: 0.4308, Val Loss: 1.4951, Val Accuracy: 0.4509 Epoch 1688/10000, Train Loss: 1.4909, Train Accuracy: 0.4397, Val Loss: 1.4949, Val Accuracy: 0.4509 Epoch 1689/10000, Train Loss: 1.4916, Train Accuracy: 0.4375, Val Loss: 1.4947, Val Accuracy: 0.4509 Epoch 1690/10000, Train Loss: 1.4925, Train Accuracy: 0.4464, Val Loss: 1.4945, Val Accuracy: 0.4509 Epoch 1691/10000, Train Loss: 1.4920, Train Accuracy: 0.4520, Val Loss: 1.4944, Val Accuracy: 0.4554 Epoch 1692/10000, Train Loss: 1.4901, Train Accuracy: 0.4397, Val Loss: 1.4942, Val Accuracy: 0.4554 Epoch 1693/10000, Train Loss: 1.4895, Train Accuracy: 0.4442, Val Loss: 1.4940, Val Accuracy: 0.4554 Epoch 1694/10000, Train Loss: 1.4920, Train Accuracy: 0.4531, Val Loss: 1.4938, Val Accuracy: 0.4554 Epoch 1695/10000, Train Loss: 1.4899, Train Accuracy: 0.4397, Val Loss: 1.4937, Val Accuracy: 0.4554 Epoch 1696/10000, Train Loss: 1.4956, Train Accuracy: 0.4498, Val Loss: 1.4936, Val Accuracy: 0.4554 Epoch 1697/10000, Train Loss: 1.4911, Train Accuracy: 0.4353, Val Loss: 1.4934, Val Accuracy: 0.4554 Epoch 1698/10000, Train Loss: 1.4884, Train Accuracy: 0.4464, Val Loss: 1.4933, Val Accuracy: 0.4554 Epoch 1699/10000, Train Loss: 1.4889, Train Accuracy: 0.4475, Val Loss: 1.4931, Val Accuracy: 0.4554 Epoch 1700/10000, Train Loss: 1.4882, Train Accuracy: 0.4353, Val Loss: 1.4930, Val Accuracy: 0.4554 Epoch 1701/10000, Train Loss: 1.4917, Train Accuracy: 0.4420, Val Loss: 1.4928, Val Accuracy: 0.4554 Epoch 1702/10000, Train Loss: 1.4902, Train Accuracy: 0.4386, Val Loss: 1.4927, Val Accuracy: 0.4554 Epoch 1703/10000, Train Loss: 1.4891, Train Accuracy: 0.4464, Val Loss: 1.4925, Val Accuracy: 0.4554 Epoch 1704/10000, Train Loss: 1.4906, Train Accuracy: 0.4353, Val Loss: 1.4924, Val Accuracy: 0.4554 Epoch 1705/10000, Train Loss: 1.4868, Train Accuracy: 0.4554, Val Loss: 1.4922, Val Accuracy: 0.4509 Epoch 1706/10000, Train Loss: 1.4921, Train Accuracy: 0.4152, Val Loss: 1.4920, Val Accuracy: 0.4554 Epoch 1707/10000, Train Loss: 1.4890, Train Accuracy: 0.4375, Val Loss: 1.4919, Val Accuracy: 0.4509 Epoch 1708/10000, Train Loss: 1.4891, Train Accuracy: 0.4330, Val Loss: 1.4916, Val Accuracy: 0.4554 Epoch 1709/10000, Train Loss: 1.4925, Train Accuracy: 0.4397, Val Loss: 1.4915, Val Accuracy: 0.4554 Epoch 1710/10000, Train Loss: 1.4917, Train Accuracy: 0.4420, Val Loss: 1.4914, Val Accuracy: 0.4554 Epoch 1711/10000, Train Loss: 1.4899, Train Accuracy: 0.4263, Val Loss: 1.4911, Val Accuracy: 0.4554 Epoch 1712/10000, Train Loss: 1.4872, Train Accuracy: 0.4297, Val Loss: 1.4910, Val Accuracy: 0.4509 Epoch 1713/10000, Train Loss: 1.4865, Train Accuracy: 0.4487, Val Loss: 1.4909, Val Accuracy: 0.4509 Epoch 1714/10000, Train Loss: 1.4863, Train Accuracy: 0.4520, Val Loss: 1.4907, Val Accuracy: 0.4509 Epoch 1715/10000, Train Loss: 1.4924, Train Accuracy: 0.4420, Val Loss: 1.4905, Val Accuracy: 0.4509 Epoch 1716/10000, Train Loss: 1.4857, Train Accuracy: 0.4375, Val Loss: 1.4903, Val Accuracy: 0.4509 Epoch 1717/10000, Train Loss: 1.4857, Train Accuracy: 0.4386, Val Loss: 1.4902, Val Accuracy: 0.4509 Epoch 1718/10000, Train Loss: 1.4866, Train Accuracy: 0.4286, Val Loss: 1.4901, Val Accuracy: 0.4554 Epoch 1719/10000, Train Loss: 1.4849, Train Accuracy: 0.4565, Val Loss: 1.4899, Val Accuracy: 0.4554 Epoch 1720/10000, Train Loss: 1.4864, Train Accuracy: 0.4397, Val Loss: 1.4897, Val Accuracy: 0.4554 Epoch 1721/10000, Train Loss: 1.4892, Train Accuracy: 0.4275, Val Loss: 1.4895, Val Accuracy: 0.4554 Epoch 1722/10000, Train Loss: 1.4863, Train Accuracy: 0.4375, Val Loss: 1.4894, Val Accuracy: 0.4554 Epoch 1723/10000, Train Loss: 1.4940, Train Accuracy: 0.4275, Val Loss: 1.4892, Val Accuracy: 0.4554 Epoch 1724/10000, Train Loss: 1.4840, Train Accuracy: 0.4297, Val Loss: 1.4891, Val Accuracy: 0.4554 Epoch 1725/10000, Train Loss: 1.4839, Train Accuracy: 0.4565, Val Loss: 1.4890, Val Accuracy: 0.4554 Epoch 1726/10000, Train Loss: 1.4825, Train Accuracy: 0.4509, Val Loss: 1.4889, Val Accuracy: 0.4554 Epoch 1727/10000, Train Loss: 1.4850, Train Accuracy: 0.4464, Val Loss: 1.4887, Val Accuracy: 0.4554 Epoch 1728/10000, Train Loss: 1.4841, Train Accuracy: 0.4442, Val Loss: 1.4885, Val Accuracy: 0.4554 Epoch 1729/10000, Train Loss: 1.4829, Train Accuracy: 0.4442, Val Loss: 1.4884, Val Accuracy: 0.4554 Epoch 1730/10000, Train Loss: 1.4860, Train Accuracy: 0.4308, Val Loss: 1.4883, Val Accuracy: 0.4554 Epoch 1731/10000, Train Loss: 1.4898, Train Accuracy: 0.4275, Val Loss: 1.4881, Val Accuracy: 0.4554 Epoch 1732/10000, Train Loss: 1.4831, Train Accuracy: 0.4453, Val Loss: 1.4880, Val Accuracy: 0.4554 Epoch 1733/10000, Train Loss: 1.4822, Train Accuracy: 0.4364, Val Loss: 1.4878, Val Accuracy: 0.4554 Epoch 1734/10000, Train Loss: 1.4883, Train Accuracy: 0.4263, Val Loss: 1.4877, Val Accuracy: 0.4554 Epoch 1735/10000, Train Loss: 1.4830, Train Accuracy: 0.4464, Val Loss: 1.4875, Val Accuracy: 0.4554 Epoch 1736/10000, Train Loss: 1.4869, Train Accuracy: 0.4475, Val Loss: 1.4874, Val Accuracy: 0.4554 Epoch 1737/10000, Train Loss: 1.4872, Train Accuracy: 0.4342, Val Loss: 1.4872, Val Accuracy: 0.4554 Epoch 1738/10000, Train Loss: 1.4891, Train Accuracy: 0.4420, Val Loss: 1.4870, Val Accuracy: 0.4554 Epoch 1739/10000, Train Loss: 1.4838, Train Accuracy: 0.4475, Val Loss: 1.4869, Val Accuracy: 0.4554 Epoch 1740/10000, Train Loss: 1.4860, Train Accuracy: 0.4487, Val Loss: 1.4867, Val Accuracy: 0.4554 Epoch 1741/10000, Train Loss: 1.4889, Train Accuracy: 0.4397, Val Loss: 1.4866, Val Accuracy: 0.4554 Epoch 1742/10000, Train Loss: 1.4842, Train Accuracy: 0.4442, Val Loss: 1.4864, Val Accuracy: 0.4554 Epoch 1743/10000, Train Loss: 1.4826, Train Accuracy: 0.4609, Val Loss: 1.4862, Val Accuracy: 0.4554 Epoch 1744/10000, Train Loss: 1.4804, Train Accuracy: 0.4498, Val Loss: 1.4861, Val Accuracy: 0.4598 Epoch 1745/10000, Train Loss: 1.4810, Train Accuracy: 0.4397, Val Loss: 1.4859, Val Accuracy: 0.4598 Epoch 1746/10000, Train Loss: 1.4835, Train Accuracy: 0.4386, Val Loss: 1.4857, Val Accuracy: 0.4598 Epoch 1747/10000, Train Loss: 1.4790, Train Accuracy: 0.4542, Val Loss: 1.4855, Val Accuracy: 0.4598 Epoch 1748/10000, Train Loss: 1.4827, Train Accuracy: 0.4654, Val Loss: 1.4853, Val Accuracy: 0.4598 Epoch 1749/10000, Train Loss: 1.4850, Train Accuracy: 0.4308, Val Loss: 1.4852, Val Accuracy: 0.4598 Epoch 1750/10000, Train Loss: 1.4811, Train Accuracy: 0.4431, Val Loss: 1.4850, Val Accuracy: 0.4598 Epoch 1751/10000, Train Loss: 1.4836, Train Accuracy: 0.4487, Val Loss: 1.4849, Val Accuracy: 0.4598 Epoch 1752/10000, Train Loss: 1.4811, Train Accuracy: 0.4587, Val Loss: 1.4847, Val Accuracy: 0.4598 Epoch 1753/10000, Train Loss: 1.4775, Train Accuracy: 0.4431, Val Loss: 1.4845, Val Accuracy: 0.4598 Epoch 1754/10000, Train Loss: 1.4818, Train Accuracy: 0.4330, Val Loss: 1.4844, Val Accuracy: 0.4598 Epoch 1755/10000, Train Loss: 1.4851, Train Accuracy: 0.4375, Val Loss: 1.4843, Val Accuracy: 0.4598 Epoch 1756/10000, Train Loss: 1.4775, Train Accuracy: 0.4475, Val Loss: 1.4841, Val Accuracy: 0.4598 Epoch 1757/10000, Train Loss: 1.4778, Train Accuracy: 0.4420, Val Loss: 1.4840, Val Accuracy: 0.4598 Epoch 1758/10000, Train Loss: 1.4760, Train Accuracy: 0.4565, Val Loss: 1.4839, Val Accuracy: 0.4598 Epoch 1759/10000, Train Loss: 1.4808, Train Accuracy: 0.4442, Val Loss: 1.4837, Val Accuracy: 0.4598 Epoch 1760/10000, Train Loss: 1.4780, Train Accuracy: 0.4587, Val Loss: 1.4836, Val Accuracy: 0.4598 Epoch 1761/10000, Train Loss: 1.4850, Train Accuracy: 0.4364, Val Loss: 1.4834, Val Accuracy: 0.4598 Epoch 1762/10000, Train Loss: 1.4810, Train Accuracy: 0.4342, Val Loss: 1.4832, Val Accuracy: 0.4598 Epoch 1763/10000, Train Loss: 1.4766, Train Accuracy: 0.4464, Val Loss: 1.4831, Val Accuracy: 0.4598 Epoch 1764/10000, Train Loss: 1.4792, Train Accuracy: 0.4542, Val Loss: 1.4829, Val Accuracy: 0.4598 Epoch 1765/10000, Train Loss: 1.4759, Train Accuracy: 0.4643, Val Loss: 1.4828, Val Accuracy: 0.4598 Epoch 1766/10000, Train Loss: 1.4740, Train Accuracy: 0.4475, Val Loss: 1.4827, Val Accuracy: 0.4598 Epoch 1767/10000, Train Loss: 1.4753, Train Accuracy: 0.4520, Val Loss: 1.4825, Val Accuracy: 0.4598 Epoch 1768/10000, Train Loss: 1.4840, Train Accuracy: 0.4397, Val Loss: 1.4823, Val Accuracy: 0.4598 Epoch 1769/10000, Train Loss: 1.4787, Train Accuracy: 0.4509, Val Loss: 1.4822, Val Accuracy: 0.4598 Epoch 1770/10000, Train Loss: 1.4764, Train Accuracy: 0.4576, Val Loss: 1.4820, Val Accuracy: 0.4598 Epoch 1771/10000, Train Loss: 1.4772, Train Accuracy: 0.4342, Val Loss: 1.4819, Val Accuracy: 0.4598 Epoch 1772/10000, Train Loss: 1.4780, Train Accuracy: 0.4386, Val Loss: 1.4818, Val Accuracy: 0.4598 Epoch 1773/10000, Train Loss: 1.4775, Train Accuracy: 0.4554, Val Loss: 1.4816, Val Accuracy: 0.4598 Epoch 1774/10000, Train Loss: 1.4822, Train Accuracy: 0.4442, Val Loss: 1.4814, Val Accuracy: 0.4598 Epoch 1775/10000, Train Loss: 1.4778, Train Accuracy: 0.4487, Val Loss: 1.4812, Val Accuracy: 0.4598 Epoch 1776/10000, Train Loss: 1.4787, Train Accuracy: 0.4531, Val Loss: 1.4811, Val Accuracy: 0.4598 Epoch 1777/10000, Train Loss: 1.4719, Train Accuracy: 0.4676, Val Loss: 1.4810, Val Accuracy: 0.4598 Epoch 1778/10000, Train Loss: 1.4777, Train Accuracy: 0.4475, Val Loss: 1.4808, Val Accuracy: 0.4598 Epoch 1779/10000, Train Loss: 1.4782, Train Accuracy: 0.4442, Val Loss: 1.4807, Val Accuracy: 0.4598 Epoch 1780/10000, Train Loss: 1.4764, Train Accuracy: 0.4654, Val Loss: 1.4805, Val Accuracy: 0.4598 Epoch 1781/10000, Train Loss: 1.4849, Train Accuracy: 0.4319, Val Loss: 1.4804, Val Accuracy: 0.4598 Epoch 1782/10000, Train Loss: 1.4718, Train Accuracy: 0.4609, Val Loss: 1.4803, Val Accuracy: 0.4598 Epoch 1783/10000, Train Loss: 1.4765, Train Accuracy: 0.4565, Val Loss: 1.4801, Val Accuracy: 0.4598 Epoch 1784/10000, Train Loss: 1.4743, Train Accuracy: 0.4487, Val Loss: 1.4800, Val Accuracy: 0.4598 Epoch 1785/10000, Train Loss: 1.4776, Train Accuracy: 0.4475, Val Loss: 1.4798, Val Accuracy: 0.4598 Epoch 1786/10000, Train Loss: 1.4742, Train Accuracy: 0.4464, Val Loss: 1.4796, Val Accuracy: 0.4598 Epoch 1787/10000, Train Loss: 1.4739, Train Accuracy: 0.4531, Val Loss: 1.4794, Val Accuracy: 0.4643 Epoch 1788/10000, Train Loss: 1.4735, Train Accuracy: 0.4542, Val Loss: 1.4793, Val Accuracy: 0.4643 Epoch 1789/10000, Train Loss: 1.4761, Train Accuracy: 0.4386, Val Loss: 1.4792, Val Accuracy: 0.4643 Epoch 1790/10000, Train Loss: 1.4754, Train Accuracy: 0.4509, Val Loss: 1.4791, Val Accuracy: 0.4643 Epoch 1791/10000, Train Loss: 1.4756, Train Accuracy: 0.4408, Val Loss: 1.4789, Val Accuracy: 0.4643 Epoch 1792/10000, Train Loss: 1.4726, Train Accuracy: 0.4565, Val Loss: 1.4787, Val Accuracy: 0.4643 Epoch 1793/10000, Train Loss: 1.4756, Train Accuracy: 0.4475, Val Loss: 1.4786, Val Accuracy: 0.4643 Epoch 1794/10000, Train Loss: 1.4772, Train Accuracy: 0.4509, Val Loss: 1.4785, Val Accuracy: 0.4643 Epoch 1795/10000, Train Loss: 1.4735, Train Accuracy: 0.4475, Val Loss: 1.4783, Val Accuracy: 0.4643 Epoch 1796/10000, Train Loss: 1.4738, Train Accuracy: 0.4576, Val Loss: 1.4781, Val Accuracy: 0.4643 Epoch 1797/10000, Train Loss: 1.4761, Train Accuracy: 0.4554, Val Loss: 1.4779, Val Accuracy: 0.4643 Epoch 1798/10000, Train Loss: 1.4722, Train Accuracy: 0.4721, Val Loss: 1.4778, Val Accuracy: 0.4643 Epoch 1799/10000, Train Loss: 1.4718, Train Accuracy: 0.4688, Val Loss: 1.4776, Val Accuracy: 0.4643 Epoch 1800/10000, Train Loss: 1.4795, Train Accuracy: 0.4554, Val Loss: 1.4775, Val Accuracy: 0.4732 Epoch 1801/10000, Train Loss: 1.4742, Train Accuracy: 0.4598, Val Loss: 1.4774, Val Accuracy: 0.4732 Epoch 1802/10000, Train Loss: 1.4709, Train Accuracy: 0.4453, Val Loss: 1.4772, Val Accuracy: 0.4732 Epoch 1803/10000, Train Loss: 1.4747, Train Accuracy: 0.4520, Val Loss: 1.4769, Val Accuracy: 0.4688 Epoch 1804/10000, Train Loss: 1.4721, Train Accuracy: 0.4520, Val Loss: 1.4768, Val Accuracy: 0.4732 Epoch 1805/10000, Train Loss: 1.4729, Train Accuracy: 0.4554, Val Loss: 1.4767, Val Accuracy: 0.4732 Epoch 1806/10000, Train Loss: 1.4730, Train Accuracy: 0.4554, Val Loss: 1.4765, Val Accuracy: 0.4732 Epoch 1807/10000, Train Loss: 1.4738, Train Accuracy: 0.4676, Val Loss: 1.4764, Val Accuracy: 0.4732 Epoch 1808/10000, Train Loss: 1.4722, Train Accuracy: 0.4632, Val Loss: 1.4762, Val Accuracy: 0.4732 Epoch 1809/10000, Train Loss: 1.4767, Train Accuracy: 0.4587, Val Loss: 1.4760, Val Accuracy: 0.4732 Epoch 1810/10000, Train Loss: 1.4738, Train Accuracy: 0.4319, Val Loss: 1.4759, Val Accuracy: 0.4732 Epoch 1811/10000, Train Loss: 1.4743, Train Accuracy: 0.4542, Val Loss: 1.4757, Val Accuracy: 0.4732 Epoch 1812/10000, Train Loss: 1.4704, Train Accuracy: 0.4699, Val Loss: 1.4756, Val Accuracy: 0.4732 Epoch 1813/10000, Train Loss: 1.4693, Train Accuracy: 0.4420, Val Loss: 1.4755, Val Accuracy: 0.4777 Epoch 1814/10000, Train Loss: 1.4735, Train Accuracy: 0.4286, Val Loss: 1.4753, Val Accuracy: 0.4777 Epoch 1815/10000, Train Loss: 1.4688, Train Accuracy: 0.4542, Val Loss: 1.4751, Val Accuracy: 0.4777 Epoch 1816/10000, Train Loss: 1.4688, Train Accuracy: 0.4464, Val Loss: 1.4750, Val Accuracy: 0.4777 Epoch 1817/10000, Train Loss: 1.4711, Train Accuracy: 0.4487, Val Loss: 1.4748, Val Accuracy: 0.4777 Epoch 1818/10000, Train Loss: 1.4685, Train Accuracy: 0.4643, Val Loss: 1.4747, Val Accuracy: 0.4777 Epoch 1819/10000, Train Loss: 1.4734, Train Accuracy: 0.4520, Val Loss: 1.4746, Val Accuracy: 0.4777 Epoch 1820/10000, Train Loss: 1.4693, Train Accuracy: 0.4609, Val Loss: 1.4745, Val Accuracy: 0.4777 Epoch 1821/10000, Train Loss: 1.4735, Train Accuracy: 0.4487, Val Loss: 1.4743, Val Accuracy: 0.4777 Epoch 1822/10000, Train Loss: 1.4724, Train Accuracy: 0.4665, Val Loss: 1.4742, Val Accuracy: 0.4777 Epoch 1823/10000, Train Loss: 1.4743, Train Accuracy: 0.4531, Val Loss: 1.4741, Val Accuracy: 0.4777 Epoch 1824/10000, Train Loss: 1.4730, Train Accuracy: 0.4487, Val Loss: 1.4739, Val Accuracy: 0.4777 Epoch 1825/10000, Train Loss: 1.4674, Train Accuracy: 0.4654, Val Loss: 1.4738, Val Accuracy: 0.4777 Epoch 1826/10000, Train Loss: 1.4672, Train Accuracy: 0.4542, Val Loss: 1.4736, Val Accuracy: 0.4777 Epoch 1827/10000, Train Loss: 1.4701, Train Accuracy: 0.4542, Val Loss: 1.4734, Val Accuracy: 0.4777 Epoch 1828/10000, Train Loss: 1.4682, Train Accuracy: 0.4420, Val Loss: 1.4733, Val Accuracy: 0.4777 Epoch 1829/10000, Train Loss: 1.4685, Train Accuracy: 0.4632, Val Loss: 1.4731, Val Accuracy: 0.4777 Epoch 1830/10000, Train Loss: 1.4665, Train Accuracy: 0.4688, Val Loss: 1.4729, Val Accuracy: 0.4777 Epoch 1831/10000, Train Loss: 1.4684, Train Accuracy: 0.4665, Val Loss: 1.4728, Val Accuracy: 0.4777 Epoch 1832/10000, Train Loss: 1.4702, Train Accuracy: 0.4632, Val Loss: 1.4726, Val Accuracy: 0.4821 Epoch 1833/10000, Train Loss: 1.4720, Train Accuracy: 0.4498, Val Loss: 1.4725, Val Accuracy: 0.4821 Epoch 1834/10000, Train Loss: 1.4698, Train Accuracy: 0.4520, Val Loss: 1.4723, Val Accuracy: 0.4821 Epoch 1835/10000, Train Loss: 1.4688, Train Accuracy: 0.4520, Val Loss: 1.4722, Val Accuracy: 0.4821 Epoch 1836/10000, Train Loss: 1.4675, Train Accuracy: 0.4621, Val Loss: 1.4720, Val Accuracy: 0.4821 Epoch 1837/10000, Train Loss: 1.4698, Train Accuracy: 0.4487, Val Loss: 1.4719, Val Accuracy: 0.4821 Epoch 1838/10000, Train Loss: 1.4666, Train Accuracy: 0.4598, Val Loss: 1.4717, Val Accuracy: 0.4777 Epoch 1839/10000, Train Loss: 1.4646, Train Accuracy: 0.4420, Val Loss: 1.4716, Val Accuracy: 0.4777 Epoch 1840/10000, Train Loss: 1.4648, Train Accuracy: 0.4699, Val Loss: 1.4715, Val Accuracy: 0.4777 Epoch 1841/10000, Train Loss: 1.4694, Train Accuracy: 0.4565, Val Loss: 1.4714, Val Accuracy: 0.4777 Epoch 1842/10000, Train Loss: 1.4697, Train Accuracy: 0.4665, Val Loss: 1.4712, Val Accuracy: 0.4821 Epoch 1843/10000, Train Loss: 1.4669, Train Accuracy: 0.4565, Val Loss: 1.4710, Val Accuracy: 0.4821 Epoch 1844/10000, Train Loss: 1.4653, Train Accuracy: 0.4397, Val Loss: 1.4709, Val Accuracy: 0.4821 Epoch 1845/10000, Train Loss: 1.4671, Train Accuracy: 0.4531, Val Loss: 1.4708, Val Accuracy: 0.4821 Epoch 1846/10000, Train Loss: 1.4699, Train Accuracy: 0.4587, Val Loss: 1.4706, Val Accuracy: 0.4821 Epoch 1847/10000, Train Loss: 1.4686, Train Accuracy: 0.4654, Val Loss: 1.4704, Val Accuracy: 0.4821 Epoch 1848/10000, Train Loss: 1.4633, Train Accuracy: 0.4420, Val Loss: 1.4703, Val Accuracy: 0.4866 Epoch 1849/10000, Train Loss: 1.4693, Train Accuracy: 0.4453, Val Loss: 1.4701, Val Accuracy: 0.4866 Epoch 1850/10000, Train Loss: 1.4660, Train Accuracy: 0.4509, Val Loss: 1.4700, Val Accuracy: 0.4866 Epoch 1851/10000, Train Loss: 1.4629, Train Accuracy: 0.4554, Val Loss: 1.4698, Val Accuracy: 0.4866 Epoch 1852/10000, Train Loss: 1.4639, Train Accuracy: 0.4665, Val Loss: 1.4697, Val Accuracy: 0.4866 Epoch 1853/10000, Train Loss: 1.4608, Train Accuracy: 0.4554, Val Loss: 1.4695, Val Accuracy: 0.4911 Epoch 1854/10000, Train Loss: 1.4647, Train Accuracy: 0.4420, Val Loss: 1.4694, Val Accuracy: 0.4911 Epoch 1855/10000, Train Loss: 1.4644, Train Accuracy: 0.4598, Val Loss: 1.4692, Val Accuracy: 0.4911 Epoch 1856/10000, Train Loss: 1.4687, Train Accuracy: 0.4475, Val Loss: 1.4691, Val Accuracy: 0.4911 Epoch 1857/10000, Train Loss: 1.4676, Train Accuracy: 0.4565, Val Loss: 1.4689, Val Accuracy: 0.4911 Epoch 1858/10000, Train Loss: 1.4639, Train Accuracy: 0.4453, Val Loss: 1.4688, Val Accuracy: 0.4911 Epoch 1859/10000, Train Loss: 1.4660, Train Accuracy: 0.4509, Val Loss: 1.4686, Val Accuracy: 0.4911 Epoch 1860/10000, Train Loss: 1.4652, Train Accuracy: 0.4676, Val Loss: 1.4685, Val Accuracy: 0.4911 Epoch 1861/10000, Train Loss: 1.4629, Train Accuracy: 0.4554, Val Loss: 1.4683, Val Accuracy: 0.4911 Epoch 1862/10000, Train Loss: 1.4648, Train Accuracy: 0.4542, Val Loss: 1.4682, Val Accuracy: 0.4911 Epoch 1863/10000, Train Loss: 1.4629, Train Accuracy: 0.4520, Val Loss: 1.4680, Val Accuracy: 0.4911 Epoch 1864/10000, Train Loss: 1.4676, Train Accuracy: 0.4643, Val Loss: 1.4679, Val Accuracy: 0.4911 Epoch 1865/10000, Train Loss: 1.4615, Train Accuracy: 0.4453, Val Loss: 1.4678, Val Accuracy: 0.4911 Epoch 1866/10000, Train Loss: 1.4645, Train Accuracy: 0.4587, Val Loss: 1.4676, Val Accuracy: 0.4911 Epoch 1867/10000, Train Loss: 1.4598, Train Accuracy: 0.4688, Val Loss: 1.4675, Val Accuracy: 0.4911 Epoch 1868/10000, Train Loss: 1.4624, Train Accuracy: 0.4587, Val Loss: 1.4674, Val Accuracy: 0.4911 Epoch 1869/10000, Train Loss: 1.4646, Train Accuracy: 0.4353, Val Loss: 1.4672, Val Accuracy: 0.4911 Epoch 1870/10000, Train Loss: 1.4631, Train Accuracy: 0.4587, Val Loss: 1.4671, Val Accuracy: 0.4911 Epoch 1871/10000, Train Loss: 1.4639, Train Accuracy: 0.4509, Val Loss: 1.4670, Val Accuracy: 0.4911 Epoch 1872/10000, Train Loss: 1.4582, Train Accuracy: 0.4754, Val Loss: 1.4668, Val Accuracy: 0.4911 Epoch 1873/10000, Train Loss: 1.4615, Train Accuracy: 0.4777, Val Loss: 1.4666, Val Accuracy: 0.4911 Epoch 1874/10000, Train Loss: 1.4647, Train Accuracy: 0.4632, Val Loss: 1.4665, Val Accuracy: 0.4911 Epoch 1875/10000, Train Loss: 1.4618, Train Accuracy: 0.4554, Val Loss: 1.4664, Val Accuracy: 0.4911 Epoch 1876/10000, Train Loss: 1.4606, Train Accuracy: 0.4643, Val Loss: 1.4663, Val Accuracy: 0.4911 Epoch 1877/10000, Train Loss: 1.4578, Train Accuracy: 0.4554, Val Loss: 1.4661, Val Accuracy: 0.4911 Epoch 1878/10000, Train Loss: 1.4615, Train Accuracy: 0.4766, Val Loss: 1.4660, Val Accuracy: 0.4911 Epoch 1879/10000, Train Loss: 1.4640, Train Accuracy: 0.4554, Val Loss: 1.4658, Val Accuracy: 0.4911 Epoch 1880/10000, Train Loss: 1.4655, Train Accuracy: 0.4520, Val Loss: 1.4657, Val Accuracy: 0.4911 Epoch 1881/10000, Train Loss: 1.4655, Train Accuracy: 0.4442, Val Loss: 1.4655, Val Accuracy: 0.4866 Epoch 1882/10000, Train Loss: 1.4576, Train Accuracy: 0.4509, Val Loss: 1.4654, Val Accuracy: 0.4911 Epoch 1883/10000, Train Loss: 1.4609, Train Accuracy: 0.4554, Val Loss: 1.4653, Val Accuracy: 0.4955 Epoch 1884/10000, Train Loss: 1.4595, Train Accuracy: 0.4632, Val Loss: 1.4651, Val Accuracy: 0.4911 Epoch 1885/10000, Train Loss: 1.4542, Train Accuracy: 0.4855, Val Loss: 1.4649, Val Accuracy: 0.4911 Epoch 1886/10000, Train Loss: 1.4600, Train Accuracy: 0.4576, Val Loss: 1.4647, Val Accuracy: 0.4911 Epoch 1887/10000, Train Loss: 1.4568, Train Accuracy: 0.4844, Val Loss: 1.4646, Val Accuracy: 0.4911 Epoch 1888/10000, Train Loss: 1.4592, Train Accuracy: 0.4821, Val Loss: 1.4645, Val Accuracy: 0.4911 Epoch 1889/10000, Train Loss: 1.4584, Train Accuracy: 0.4721, Val Loss: 1.4643, Val Accuracy: 0.4911 Epoch 1890/10000, Train Loss: 1.4606, Train Accuracy: 0.4665, Val Loss: 1.4641, Val Accuracy: 0.4911 Epoch 1891/10000, Train Loss: 1.4635, Train Accuracy: 0.4643, Val Loss: 1.4640, Val Accuracy: 0.4911 Epoch 1892/10000, Train Loss: 1.4562, Train Accuracy: 0.4743, Val Loss: 1.4639, Val Accuracy: 0.4955 Epoch 1893/10000, Train Loss: 1.4586, Train Accuracy: 0.4699, Val Loss: 1.4638, Val Accuracy: 0.4955 Epoch 1894/10000, Train Loss: 1.4564, Train Accuracy: 0.4632, Val Loss: 1.4637, Val Accuracy: 0.4955 Epoch 1895/10000, Train Loss: 1.4615, Train Accuracy: 0.4598, Val Loss: 1.4635, Val Accuracy: 0.4955 Epoch 1896/10000, Train Loss: 1.4604, Train Accuracy: 0.4509, Val Loss: 1.4634, Val Accuracy: 0.4955 Epoch 1897/10000, Train Loss: 1.4595, Train Accuracy: 0.4766, Val Loss: 1.4632, Val Accuracy: 0.4955 Epoch 1898/10000, Train Loss: 1.4623, Train Accuracy: 0.4453, Val Loss: 1.4631, Val Accuracy: 0.4955 Epoch 1899/10000, Train Loss: 1.4575, Train Accuracy: 0.4710, Val Loss: 1.4630, Val Accuracy: 0.4955 Epoch 1900/10000, Train Loss: 1.4611, Train Accuracy: 0.4643, Val Loss: 1.4629, Val Accuracy: 0.4955 Epoch 1901/10000, Train Loss: 1.4644, Train Accuracy: 0.4587, Val Loss: 1.4627, Val Accuracy: 0.4955 Epoch 1902/10000, Train Loss: 1.4542, Train Accuracy: 0.4911, Val Loss: 1.4626, Val Accuracy: 0.4955 Epoch 1903/10000, Train Loss: 1.4574, Train Accuracy: 0.4688, Val Loss: 1.4625, Val Accuracy: 0.4955 Epoch 1904/10000, Train Loss: 1.4560, Train Accuracy: 0.4777, Val Loss: 1.4624, Val Accuracy: 0.4955 Epoch 1905/10000, Train Loss: 1.4562, Train Accuracy: 0.4721, Val Loss: 1.4622, Val Accuracy: 0.4955 Epoch 1906/10000, Train Loss: 1.4579, Train Accuracy: 0.4542, Val Loss: 1.4620, Val Accuracy: 0.4955 Epoch 1907/10000, Train Loss: 1.4546, Train Accuracy: 0.4699, Val Loss: 1.4619, Val Accuracy: 0.4955 Epoch 1908/10000, Train Loss: 1.4523, Train Accuracy: 0.4587, Val Loss: 1.4617, Val Accuracy: 0.4955 Epoch 1909/10000, Train Loss: 1.4530, Train Accuracy: 0.4788, Val Loss: 1.4616, Val Accuracy: 0.4955 Epoch 1910/10000, Train Loss: 1.4528, Train Accuracy: 0.4788, Val Loss: 1.4614, Val Accuracy: 0.4955 Epoch 1911/10000, Train Loss: 1.4488, Train Accuracy: 0.4967, Val Loss: 1.4613, Val Accuracy: 0.4955 Epoch 1912/10000, Train Loss: 1.4550, Train Accuracy: 0.4732, Val Loss: 1.4611, Val Accuracy: 0.4955 Epoch 1913/10000, Train Loss: 1.4534, Train Accuracy: 0.4777, Val Loss: 1.4610, Val Accuracy: 0.4955 Epoch 1914/10000, Train Loss: 1.4558, Train Accuracy: 0.4453, Val Loss: 1.4609, Val Accuracy: 0.4955 Epoch 1915/10000, Train Loss: 1.4546, Train Accuracy: 0.4710, Val Loss: 1.4608, Val Accuracy: 0.4955 Epoch 1916/10000, Train Loss: 1.4604, Train Accuracy: 0.4732, Val Loss: 1.4606, Val Accuracy: 0.4955 Epoch 1917/10000, Train Loss: 1.4548, Train Accuracy: 0.4632, Val Loss: 1.4604, Val Accuracy: 0.4955 Epoch 1918/10000, Train Loss: 1.4568, Train Accuracy: 0.4688, Val Loss: 1.4603, Val Accuracy: 0.4955 Epoch 1919/10000, Train Loss: 1.4523, Train Accuracy: 0.4710, Val Loss: 1.4602, Val Accuracy: 0.4955 Epoch 1920/10000, Train Loss: 1.4490, Train Accuracy: 0.4821, Val Loss: 1.4600, Val Accuracy: 0.4955 Epoch 1921/10000, Train Loss: 1.4575, Train Accuracy: 0.4576, Val Loss: 1.4599, Val Accuracy: 0.4911 Epoch 1922/10000, Train Loss: 1.4515, Train Accuracy: 0.4688, Val Loss: 1.4598, Val Accuracy: 0.4911 Epoch 1923/10000, Train Loss: 1.4567, Train Accuracy: 0.4554, Val Loss: 1.4596, Val Accuracy: 0.4911 Epoch 1924/10000, Train Loss: 1.4574, Train Accuracy: 0.4721, Val Loss: 1.4594, Val Accuracy: 0.4911 Epoch 1925/10000, Train Loss: 1.4538, Train Accuracy: 0.4665, Val Loss: 1.4593, Val Accuracy: 0.4911 Epoch 1926/10000, Train Loss: 1.4528, Train Accuracy: 0.4654, Val Loss: 1.4591, Val Accuracy: 0.4911 Epoch 1927/10000, Train Loss: 1.4529, Train Accuracy: 0.4743, Val Loss: 1.4590, Val Accuracy: 0.4911 Epoch 1928/10000, Train Loss: 1.4542, Train Accuracy: 0.4810, Val Loss: 1.4589, Val Accuracy: 0.4911 Epoch 1929/10000, Train Loss: 1.4539, Train Accuracy: 0.4498, Val Loss: 1.4588, Val Accuracy: 0.4955 Epoch 1930/10000, Train Loss: 1.4533, Train Accuracy: 0.4710, Val Loss: 1.4587, Val Accuracy: 0.4955 Epoch 1931/10000, Train Loss: 1.4509, Train Accuracy: 0.4721, Val Loss: 1.4585, Val Accuracy: 0.4911 Epoch 1932/10000, Train Loss: 1.4474, Train Accuracy: 0.4844, Val Loss: 1.4584, Val Accuracy: 0.4955 Epoch 1933/10000, Train Loss: 1.4486, Train Accuracy: 0.4833, Val Loss: 1.4583, Val Accuracy: 0.4955 Epoch 1934/10000, Train Loss: 1.4493, Train Accuracy: 0.4676, Val Loss: 1.4581, Val Accuracy: 0.4955 Epoch 1935/10000, Train Loss: 1.4560, Train Accuracy: 0.4732, Val Loss: 1.4580, Val Accuracy: 0.4955 Epoch 1936/10000, Train Loss: 1.4548, Train Accuracy: 0.4710, Val Loss: 1.4579, Val Accuracy: 0.4955 Epoch 1937/10000, Train Loss: 1.4500, Train Accuracy: 0.4732, Val Loss: 1.4576, Val Accuracy: 0.4955 Epoch 1938/10000, Train Loss: 1.4496, Train Accuracy: 0.4766, Val Loss: 1.4574, Val Accuracy: 0.5000 Epoch 1939/10000, Train Loss: 1.4489, Train Accuracy: 0.4844, Val Loss: 1.4572, Val Accuracy: 0.5000 Epoch 1940/10000, Train Loss: 1.4510, Train Accuracy: 0.4743, Val Loss: 1.4572, Val Accuracy: 0.4955 Epoch 1941/10000, Train Loss: 1.4470, Train Accuracy: 0.4955, Val Loss: 1.4570, Val Accuracy: 0.5000 Epoch 1942/10000, Train Loss: 1.4533, Train Accuracy: 0.4710, Val Loss: 1.4569, Val Accuracy: 0.5000 Epoch 1943/10000, Train Loss: 1.4524, Train Accuracy: 0.4699, Val Loss: 1.4568, Val Accuracy: 0.5000 Epoch 1944/10000, Train Loss: 1.4497, Train Accuracy: 0.4598, Val Loss: 1.4567, Val Accuracy: 0.5000 Epoch 1945/10000, Train Loss: 1.4538, Train Accuracy: 0.4777, Val Loss: 1.4566, Val Accuracy: 0.5000 Epoch 1946/10000, Train Loss: 1.4568, Train Accuracy: 0.4598, Val Loss: 1.4564, Val Accuracy: 0.5000 Epoch 1947/10000, Train Loss: 1.4485, Train Accuracy: 0.4788, Val Loss: 1.4563, Val Accuracy: 0.5000 Epoch 1948/10000, Train Loss: 1.4520, Train Accuracy: 0.4754, Val Loss: 1.4561, Val Accuracy: 0.5000 Epoch 1949/10000, Train Loss: 1.4500, Train Accuracy: 0.4900, Val Loss: 1.4560, Val Accuracy: 0.5000 Epoch 1950/10000, Train Loss: 1.4519, Train Accuracy: 0.4810, Val Loss: 1.4559, Val Accuracy: 0.5000 Epoch 1951/10000, Train Loss: 1.4532, Train Accuracy: 0.4900, Val Loss: 1.4558, Val Accuracy: 0.5000 Epoch 1952/10000, Train Loss: 1.4484, Train Accuracy: 0.4978, Val Loss: 1.4557, Val Accuracy: 0.5000 Epoch 1953/10000, Train Loss: 1.4505, Train Accuracy: 0.4866, Val Loss: 1.4555, Val Accuracy: 0.5000 Epoch 1954/10000, Train Loss: 1.4533, Train Accuracy: 0.4766, Val Loss: 1.4553, Val Accuracy: 0.5000 Epoch 1955/10000, Train Loss: 1.4537, Train Accuracy: 0.4609, Val Loss: 1.4552, Val Accuracy: 0.5000 Epoch 1956/10000, Train Loss: 1.4500, Train Accuracy: 0.4844, Val Loss: 1.4551, Val Accuracy: 0.5000 Epoch 1957/10000, Train Loss: 1.4551, Train Accuracy: 0.4688, Val Loss: 1.4550, Val Accuracy: 0.5000 Epoch 1958/10000, Train Loss: 1.4504, Train Accuracy: 0.4732, Val Loss: 1.4548, Val Accuracy: 0.5000 Epoch 1959/10000, Train Loss: 1.4535, Train Accuracy: 0.4621, Val Loss: 1.4547, Val Accuracy: 0.5000 Epoch 1960/10000, Train Loss: 1.4513, Train Accuracy: 0.4732, Val Loss: 1.4546, Val Accuracy: 0.5000 Epoch 1961/10000, Train Loss: 1.4482, Train Accuracy: 0.4676, Val Loss: 1.4544, Val Accuracy: 0.5000 Epoch 1962/10000, Train Loss: 1.4499, Train Accuracy: 0.4866, Val Loss: 1.4543, Val Accuracy: 0.5000 Epoch 1963/10000, Train Loss: 1.4565, Train Accuracy: 0.4643, Val Loss: 1.4542, Val Accuracy: 0.5000 Epoch 1964/10000, Train Loss: 1.4533, Train Accuracy: 0.4877, Val Loss: 1.4541, Val Accuracy: 0.5045 Epoch 1965/10000, Train Loss: 1.4500, Train Accuracy: 0.4621, Val Loss: 1.4539, Val Accuracy: 0.5045 Epoch 1966/10000, Train Loss: 1.4502, Train Accuracy: 0.4844, Val Loss: 1.4538, Val Accuracy: 0.5045 Epoch 1967/10000, Train Loss: 1.4487, Train Accuracy: 0.4922, Val Loss: 1.4537, Val Accuracy: 0.5045 Epoch 1968/10000, Train Loss: 1.4446, Train Accuracy: 0.4766, Val Loss: 1.4536, Val Accuracy: 0.5045 Epoch 1969/10000, Train Loss: 1.4485, Train Accuracy: 0.4788, Val Loss: 1.4534, Val Accuracy: 0.5045 Epoch 1970/10000, Train Loss: 1.4501, Train Accuracy: 0.4754, Val Loss: 1.4533, Val Accuracy: 0.5045 Epoch 1971/10000, Train Loss: 1.4474, Train Accuracy: 0.4833, Val Loss: 1.4532, Val Accuracy: 0.5045 Epoch 1972/10000, Train Loss: 1.4455, Train Accuracy: 0.4855, Val Loss: 1.4530, Val Accuracy: 0.5045 Epoch 1973/10000, Train Loss: 1.4488, Train Accuracy: 0.4833, Val Loss: 1.4530, Val Accuracy: 0.5045 Epoch 1974/10000, Train Loss: 1.4552, Train Accuracy: 0.4721, Val Loss: 1.4528, Val Accuracy: 0.5045 Epoch 1975/10000, Train Loss: 1.4490, Train Accuracy: 0.4676, Val Loss: 1.4527, Val Accuracy: 0.5045 Epoch 1976/10000, Train Loss: 1.4466, Train Accuracy: 0.4821, Val Loss: 1.4525, Val Accuracy: 0.5045 Epoch 1977/10000, Train Loss: 1.4386, Train Accuracy: 0.5000, Val Loss: 1.4524, Val Accuracy: 0.5000 Epoch 1978/10000, Train Loss: 1.4431, Train Accuracy: 0.4911, Val Loss: 1.4522, Val Accuracy: 0.5000 Epoch 1979/10000, Train Loss: 1.4456, Train Accuracy: 0.4866, Val Loss: 1.4521, Val Accuracy: 0.5000 Epoch 1980/10000, Train Loss: 1.4420, Train Accuracy: 0.4877, Val Loss: 1.4520, Val Accuracy: 0.5000 Epoch 1981/10000, Train Loss: 1.4467, Train Accuracy: 0.4944, Val Loss: 1.4519, Val Accuracy: 0.5000 Epoch 1982/10000, Train Loss: 1.4467, Train Accuracy: 0.4821, Val Loss: 1.4517, Val Accuracy: 0.5000 Epoch 1983/10000, Train Loss: 1.4456, Train Accuracy: 0.5011, Val Loss: 1.4515, Val Accuracy: 0.5000 Epoch 1984/10000, Train Loss: 1.4449, Train Accuracy: 0.4777, Val Loss: 1.4514, Val Accuracy: 0.5000 Epoch 1985/10000, Train Loss: 1.4470, Train Accuracy: 0.4799, Val Loss: 1.4513, Val Accuracy: 0.5045 Epoch 1986/10000, Train Loss: 1.4484, Train Accuracy: 0.4810, Val Loss: 1.4512, Val Accuracy: 0.5045 Epoch 1987/10000, Train Loss: 1.4464, Train Accuracy: 0.4732, Val Loss: 1.4510, Val Accuracy: 0.5045 Epoch 1988/10000, Train Loss: 1.4449, Train Accuracy: 0.4967, Val Loss: 1.4509, Val Accuracy: 0.5045 Epoch 1989/10000, Train Loss: 1.4432, Train Accuracy: 0.5000, Val Loss: 1.4507, Val Accuracy: 0.5045 Epoch 1990/10000, Train Loss: 1.4446, Train Accuracy: 0.4933, Val Loss: 1.4506, Val Accuracy: 0.5045 Epoch 1991/10000, Train Loss: 1.4422, Train Accuracy: 0.4833, Val Loss: 1.4505, Val Accuracy: 0.5045 Epoch 1992/10000, Train Loss: 1.4402, Train Accuracy: 0.5078, Val Loss: 1.4503, Val Accuracy: 0.5045 Epoch 1993/10000, Train Loss: 1.4426, Train Accuracy: 0.4732, Val Loss: 1.4502, Val Accuracy: 0.5045 Epoch 1994/10000, Train Loss: 1.4401, Train Accuracy: 0.5033, Val Loss: 1.4500, Val Accuracy: 0.5045 Epoch 1995/10000, Train Loss: 1.4414, Train Accuracy: 0.4933, Val Loss: 1.4499, Val Accuracy: 0.5045 Epoch 1996/10000, Train Loss: 1.4421, Train Accuracy: 0.4955, Val Loss: 1.4498, Val Accuracy: 0.5045 Epoch 1997/10000, Train Loss: 1.4454, Train Accuracy: 0.4944, Val Loss: 1.4496, Val Accuracy: 0.5045 Epoch 1998/10000, Train Loss: 1.4442, Train Accuracy: 0.4877, Val Loss: 1.4494, Val Accuracy: 0.5045 Epoch 1999/10000, Train Loss: 1.4471, Train Accuracy: 0.4888, Val Loss: 1.4494, Val Accuracy: 0.5045 Epoch 2000/10000, Train Loss: 1.4421, Train Accuracy: 0.4900, Val Loss: 1.4493, Val Accuracy: 0.5089 Epoch 2001/10000, Train Loss: 1.4453, Train Accuracy: 0.4732, Val Loss: 1.4492, Val Accuracy: 0.5089 Epoch 2002/10000, Train Loss: 1.4431, Train Accuracy: 0.4721, Val Loss: 1.4490, Val Accuracy: 0.5089 Epoch 2003/10000, Train Loss: 1.4496, Train Accuracy: 0.4766, Val Loss: 1.4489, Val Accuracy: 0.5089 Epoch 2004/10000, Train Loss: 1.4437, Train Accuracy: 0.4710, Val Loss: 1.4487, Val Accuracy: 0.5089 Epoch 2005/10000, Train Loss: 1.4396, Train Accuracy: 0.4821, Val Loss: 1.4486, Val Accuracy: 0.5089 Epoch 2006/10000, Train Loss: 1.4449, Train Accuracy: 0.4833, Val Loss: 1.4485, Val Accuracy: 0.5089 Epoch 2007/10000, Train Loss: 1.4405, Train Accuracy: 0.4944, Val Loss: 1.4484, Val Accuracy: 0.5045 Epoch 2008/10000, Train Loss: 1.4403, Train Accuracy: 0.5123, Val Loss: 1.4483, Val Accuracy: 0.5045 Epoch 2009/10000, Train Loss: 1.4429, Train Accuracy: 0.4788, Val Loss: 1.4481, Val Accuracy: 0.5045 Epoch 2010/10000, Train Loss: 1.4452, Train Accuracy: 0.4565, Val Loss: 1.4480, Val Accuracy: 0.5045 Epoch 2011/10000, Train Loss: 1.4394, Train Accuracy: 0.4799, Val Loss: 1.4479, Val Accuracy: 0.5045 Epoch 2012/10000, Train Loss: 1.4438, Train Accuracy: 0.4866, Val Loss: 1.4477, Val Accuracy: 0.5045 Epoch 2013/10000, Train Loss: 1.4419, Train Accuracy: 0.4944, Val Loss: 1.4476, Val Accuracy: 0.5045 Epoch 2014/10000, Train Loss: 1.4416, Train Accuracy: 0.4933, Val Loss: 1.4475, Val Accuracy: 0.5045 Epoch 2015/10000, Train Loss: 1.4398, Train Accuracy: 0.4766, Val Loss: 1.4473, Val Accuracy: 0.5045 Epoch 2016/10000, Train Loss: 1.4377, Train Accuracy: 0.4855, Val Loss: 1.4472, Val Accuracy: 0.5045 Epoch 2017/10000, Train Loss: 1.4393, Train Accuracy: 0.5156, Val Loss: 1.4471, Val Accuracy: 0.5045 Epoch 2018/10000, Train Loss: 1.4432, Train Accuracy: 0.4877, Val Loss: 1.4470, Val Accuracy: 0.5045 Epoch 2019/10000, Train Loss: 1.4420, Train Accuracy: 0.5011, Val Loss: 1.4468, Val Accuracy: 0.5045 Epoch 2020/10000, Train Loss: 1.4394, Train Accuracy: 0.4810, Val Loss: 1.4467, Val Accuracy: 0.5045 Epoch 2021/10000, Train Loss: 1.4351, Train Accuracy: 0.4989, Val Loss: 1.4466, Val Accuracy: 0.5045 Epoch 2022/10000, Train Loss: 1.4352, Train Accuracy: 0.4978, Val Loss: 1.4464, Val Accuracy: 0.5045 Epoch 2023/10000, Train Loss: 1.4388, Train Accuracy: 0.5022, Val Loss: 1.4463, Val Accuracy: 0.5045 Epoch 2024/10000, Train Loss: 1.4374, Train Accuracy: 0.4877, Val Loss: 1.4462, Val Accuracy: 0.5045 Epoch 2025/10000, Train Loss: 1.4414, Train Accuracy: 0.4777, Val Loss: 1.4460, Val Accuracy: 0.5045 Epoch 2026/10000, Train Loss: 1.4426, Train Accuracy: 0.4866, Val Loss: 1.4459, Val Accuracy: 0.5045 Epoch 2027/10000, Train Loss: 1.4410, Train Accuracy: 0.4877, Val Loss: 1.4457, Val Accuracy: 0.5045 Epoch 2028/10000, Train Loss: 1.4365, Train Accuracy: 0.4955, Val Loss: 1.4456, Val Accuracy: 0.5045 Epoch 2029/10000, Train Loss: 1.4391, Train Accuracy: 0.4922, Val Loss: 1.4454, Val Accuracy: 0.5045 Epoch 2030/10000, Train Loss: 1.4370, Train Accuracy: 0.5145, Val Loss: 1.4453, Val Accuracy: 0.5045 Epoch 2031/10000, Train Loss: 1.4391, Train Accuracy: 0.5067, Val Loss: 1.4452, Val Accuracy: 0.5045 Epoch 2032/10000, Train Loss: 1.4389, Train Accuracy: 0.4877, Val Loss: 1.4451, Val Accuracy: 0.5045 Epoch 2033/10000, Train Loss: 1.4353, Train Accuracy: 0.4978, Val Loss: 1.4450, Val Accuracy: 0.5045 Epoch 2034/10000, Train Loss: 1.4346, Train Accuracy: 0.4922, Val Loss: 1.4449, Val Accuracy: 0.5045 Epoch 2035/10000, Train Loss: 1.4366, Train Accuracy: 0.5045, Val Loss: 1.4447, Val Accuracy: 0.5045 Epoch 2036/10000, Train Loss: 1.4357, Train Accuracy: 0.4978, Val Loss: 1.4446, Val Accuracy: 0.5045 Epoch 2037/10000, Train Loss: 1.4345, Train Accuracy: 0.4989, Val Loss: 1.4445, Val Accuracy: 0.5045 Epoch 2038/10000, Train Loss: 1.4402, Train Accuracy: 0.4866, Val Loss: 1.4444, Val Accuracy: 0.5045 Epoch 2039/10000, Train Loss: 1.4391, Train Accuracy: 0.4967, Val Loss: 1.4443, Val Accuracy: 0.5045 Epoch 2040/10000, Train Loss: 1.4410, Train Accuracy: 0.4978, Val Loss: 1.4441, Val Accuracy: 0.5045 Epoch 2041/10000, Train Loss: 1.4362, Train Accuracy: 0.5067, Val Loss: 1.4440, Val Accuracy: 0.5000 Epoch 2042/10000, Train Loss: 1.4338, Train Accuracy: 0.5056, Val Loss: 1.4439, Val Accuracy: 0.5000 Epoch 2043/10000, Train Loss: 1.4400, Train Accuracy: 0.4866, Val Loss: 1.4438, Val Accuracy: 0.5000 Epoch 2044/10000, Train Loss: 1.4343, Train Accuracy: 0.5112, Val Loss: 1.4436, Val Accuracy: 0.5045 Epoch 2045/10000, Train Loss: 1.4366, Train Accuracy: 0.4989, Val Loss: 1.4436, Val Accuracy: 0.5045 Epoch 2046/10000, Train Loss: 1.4336, Train Accuracy: 0.5134, Val Loss: 1.4434, Val Accuracy: 0.5045 Epoch 2047/10000, Train Loss: 1.4362, Train Accuracy: 0.5179, Val Loss: 1.4433, Val Accuracy: 0.5000 Epoch 2048/10000, Train Loss: 1.4344, Train Accuracy: 0.4900, Val Loss: 1.4432, Val Accuracy: 0.5045 Epoch 2049/10000, Train Loss: 1.4377, Train Accuracy: 0.5234, Val Loss: 1.4431, Val Accuracy: 0.5045 Epoch 2050/10000, Train Loss: 1.4358, Train Accuracy: 0.4944, Val Loss: 1.4430, Val Accuracy: 0.5045 Epoch 2051/10000, Train Loss: 1.4391, Train Accuracy: 0.4833, Val Loss: 1.4428, Val Accuracy: 0.5089 Epoch 2052/10000, Train Loss: 1.4281, Train Accuracy: 0.5112, Val Loss: 1.4427, Val Accuracy: 0.5089 Epoch 2053/10000, Train Loss: 1.4350, Train Accuracy: 0.5000, Val Loss: 1.4424, Val Accuracy: 0.5089 Epoch 2054/10000, Train Loss: 1.4373, Train Accuracy: 0.5022, Val Loss: 1.4423, Val Accuracy: 0.5089 Epoch 2055/10000, Train Loss: 1.4401, Train Accuracy: 0.5078, Val Loss: 1.4422, Val Accuracy: 0.5045 Epoch 2056/10000, Train Loss: 1.4387, Train Accuracy: 0.5033, Val Loss: 1.4421, Val Accuracy: 0.5089 Epoch 2057/10000, Train Loss: 1.4298, Train Accuracy: 0.5145, Val Loss: 1.4419, Val Accuracy: 0.5045 Epoch 2058/10000, Train Loss: 1.4340, Train Accuracy: 0.4967, Val Loss: 1.4417, Val Accuracy: 0.5089 Epoch 2059/10000, Train Loss: 1.4353, Train Accuracy: 0.5156, Val Loss: 1.4416, Val Accuracy: 0.5134 Epoch 2060/10000, Train Loss: 1.4371, Train Accuracy: 0.5123, Val Loss: 1.4415, Val Accuracy: 0.5134 Epoch 2061/10000, Train Loss: 1.4344, Train Accuracy: 0.4922, Val Loss: 1.4414, Val Accuracy: 0.5089 Epoch 2062/10000, Train Loss: 1.4351, Train Accuracy: 0.4911, Val Loss: 1.4413, Val Accuracy: 0.5089 Epoch 2063/10000, Train Loss: 1.4314, Train Accuracy: 0.5167, Val Loss: 1.4412, Val Accuracy: 0.5134 Epoch 2064/10000, Train Loss: 1.4313, Train Accuracy: 0.5078, Val Loss: 1.4411, Val Accuracy: 0.5134 Epoch 2065/10000, Train Loss: 1.4351, Train Accuracy: 0.5022, Val Loss: 1.4409, Val Accuracy: 0.5134 Epoch 2066/10000, Train Loss: 1.4319, Train Accuracy: 0.5156, Val Loss: 1.4408, Val Accuracy: 0.5134 Epoch 2067/10000, Train Loss: 1.4417, Train Accuracy: 0.4799, Val Loss: 1.4407, Val Accuracy: 0.5134 Epoch 2068/10000, Train Loss: 1.4326, Train Accuracy: 0.5056, Val Loss: 1.4406, Val Accuracy: 0.5134 Epoch 2069/10000, Train Loss: 1.4340, Train Accuracy: 0.5011, Val Loss: 1.4405, Val Accuracy: 0.5134 Epoch 2070/10000, Train Loss: 1.4321, Train Accuracy: 0.5056, Val Loss: 1.4404, Val Accuracy: 0.5134 Epoch 2071/10000, Train Loss: 1.4358, Train Accuracy: 0.5067, Val Loss: 1.4402, Val Accuracy: 0.5134 Epoch 2072/10000, Train Loss: 1.4284, Train Accuracy: 0.5234, Val Loss: 1.4401, Val Accuracy: 0.5134 Epoch 2073/10000, Train Loss: 1.4265, Train Accuracy: 0.5179, Val Loss: 1.4400, Val Accuracy: 0.5134 Epoch 2074/10000, Train Loss: 1.4360, Train Accuracy: 0.5067, Val Loss: 1.4398, Val Accuracy: 0.5134 Epoch 2075/10000, Train Loss: 1.4307, Train Accuracy: 0.5201, Val Loss: 1.4397, Val Accuracy: 0.5134 Epoch 2076/10000, Train Loss: 1.4316, Train Accuracy: 0.5100, Val Loss: 1.4396, Val Accuracy: 0.5134 Epoch 2077/10000, Train Loss: 1.4297, Train Accuracy: 0.5190, Val Loss: 1.4395, Val Accuracy: 0.5134 Epoch 2078/10000, Train Loss: 1.4325, Train Accuracy: 0.5011, Val Loss: 1.4394, Val Accuracy: 0.5134 Epoch 2079/10000, Train Loss: 1.4295, Train Accuracy: 0.4967, Val Loss: 1.4392, Val Accuracy: 0.5134 Epoch 2080/10000, Train Loss: 1.4368, Train Accuracy: 0.4989, Val Loss: 1.4391, Val Accuracy: 0.5134 Epoch 2081/10000, Train Loss: 1.4228, Train Accuracy: 0.5290, Val Loss: 1.4390, Val Accuracy: 0.5134 Epoch 2082/10000, Train Loss: 1.4296, Train Accuracy: 0.5246, Val Loss: 1.4389, Val Accuracy: 0.5134 Epoch 2083/10000, Train Loss: 1.4259, Train Accuracy: 0.5201, Val Loss: 1.4388, Val Accuracy: 0.5134 Epoch 2084/10000, Train Loss: 1.4290, Train Accuracy: 0.5011, Val Loss: 1.4387, Val Accuracy: 0.5134 Epoch 2085/10000, Train Loss: 1.4284, Train Accuracy: 0.5100, Val Loss: 1.4387, Val Accuracy: 0.5134 Epoch 2086/10000, Train Loss: 1.4298, Train Accuracy: 0.5167, Val Loss: 1.4385, Val Accuracy: 0.5134 Epoch 2087/10000, Train Loss: 1.4280, Train Accuracy: 0.5123, Val Loss: 1.4384, Val Accuracy: 0.5134 Epoch 2088/10000, Train Loss: 1.4244, Train Accuracy: 0.5190, Val Loss: 1.4382, Val Accuracy: 0.5134 Epoch 2089/10000, Train Loss: 1.4282, Train Accuracy: 0.5223, Val Loss: 1.4381, Val Accuracy: 0.5134 Epoch 2090/10000, Train Loss: 1.4302, Train Accuracy: 0.4933, Val Loss: 1.4380, Val Accuracy: 0.5134 Epoch 2091/10000, Train Loss: 1.4281, Train Accuracy: 0.5112, Val Loss: 1.4378, Val Accuracy: 0.5134 Epoch 2092/10000, Train Loss: 1.4298, Train Accuracy: 0.5011, Val Loss: 1.4377, Val Accuracy: 0.5179 Epoch 2093/10000, Train Loss: 1.4373, Train Accuracy: 0.5000, Val Loss: 1.4376, Val Accuracy: 0.5179 Epoch 2094/10000, Train Loss: 1.4270, Train Accuracy: 0.5089, Val Loss: 1.4375, Val Accuracy: 0.5179 Epoch 2095/10000, Train Loss: 1.4306, Train Accuracy: 0.5056, Val Loss: 1.4373, Val Accuracy: 0.5179 Epoch 2096/10000, Train Loss: 1.4253, Train Accuracy: 0.5045, Val Loss: 1.4372, Val Accuracy: 0.5179 Epoch 2097/10000, Train Loss: 1.4287, Train Accuracy: 0.5123, Val Loss: 1.4371, Val Accuracy: 0.5179 Epoch 2098/10000, Train Loss: 1.4235, Train Accuracy: 0.5379, Val Loss: 1.4369, Val Accuracy: 0.5179 Epoch 2099/10000, Train Loss: 1.4295, Train Accuracy: 0.4978, Val Loss: 1.4368, Val Accuracy: 0.5223 Epoch 2100/10000, Train Loss: 1.4273, Train Accuracy: 0.4978, Val Loss: 1.4367, Val Accuracy: 0.5268 Epoch 2101/10000, Train Loss: 1.4250, Train Accuracy: 0.5100, Val Loss: 1.4366, Val Accuracy: 0.5268 Epoch 2102/10000, Train Loss: 1.4274, Train Accuracy: 0.5067, Val Loss: 1.4364, Val Accuracy: 0.5268 Epoch 2103/10000, Train Loss: 1.4286, Train Accuracy: 0.5056, Val Loss: 1.4362, Val Accuracy: 0.5223 Epoch 2104/10000, Train Loss: 1.4303, Train Accuracy: 0.5145, Val Loss: 1.4362, Val Accuracy: 0.5223 Epoch 2105/10000, Train Loss: 1.4300, Train Accuracy: 0.5089, Val Loss: 1.4361, Val Accuracy: 0.5223 Epoch 2106/10000, Train Loss: 1.4278, Train Accuracy: 0.5223, Val Loss: 1.4360, Val Accuracy: 0.5268 Epoch 2107/10000, Train Loss: 1.4243, Train Accuracy: 0.5089, Val Loss: 1.4358, Val Accuracy: 0.5268 Epoch 2108/10000, Train Loss: 1.4248, Train Accuracy: 0.5067, Val Loss: 1.4357, Val Accuracy: 0.5268 Epoch 2109/10000, Train Loss: 1.4274, Train Accuracy: 0.5112, Val Loss: 1.4356, Val Accuracy: 0.5268 Epoch 2110/10000, Train Loss: 1.4245, Train Accuracy: 0.5145, Val Loss: 1.4354, Val Accuracy: 0.5223 Epoch 2111/10000, Train Loss: 1.4262, Train Accuracy: 0.5156, Val Loss: 1.4353, Val Accuracy: 0.5223 Epoch 2112/10000, Train Loss: 1.4283, Train Accuracy: 0.5045, Val Loss: 1.4352, Val Accuracy: 0.5223 Epoch 2113/10000, Train Loss: 1.4307, Train Accuracy: 0.5145, Val Loss: 1.4350, Val Accuracy: 0.5223 Epoch 2114/10000, Train Loss: 1.4268, Train Accuracy: 0.5201, Val Loss: 1.4349, Val Accuracy: 0.5223 Epoch 2115/10000, Train Loss: 1.4238, Train Accuracy: 0.5045, Val Loss: 1.4348, Val Accuracy: 0.5223 Epoch 2116/10000, Train Loss: 1.4222, Train Accuracy: 0.5246, Val Loss: 1.4347, Val Accuracy: 0.5223 Epoch 2117/10000, Train Loss: 1.4200, Train Accuracy: 0.5312, Val Loss: 1.4345, Val Accuracy: 0.5223 Epoch 2118/10000, Train Loss: 1.4195, Train Accuracy: 0.5558, Val Loss: 1.4344, Val Accuracy: 0.5223 Epoch 2119/10000, Train Loss: 1.4290, Train Accuracy: 0.5067, Val Loss: 1.4342, Val Accuracy: 0.5223 Epoch 2120/10000, Train Loss: 1.4279, Train Accuracy: 0.5033, Val Loss: 1.4341, Val Accuracy: 0.5223 Epoch 2121/10000, Train Loss: 1.4277, Train Accuracy: 0.5022, Val Loss: 1.4340, Val Accuracy: 0.5223 Epoch 2122/10000, Train Loss: 1.4232, Train Accuracy: 0.5100, Val Loss: 1.4338, Val Accuracy: 0.5223 Epoch 2123/10000, Train Loss: 1.4275, Train Accuracy: 0.5156, Val Loss: 1.4338, Val Accuracy: 0.5179 Epoch 2124/10000, Train Loss: 1.4235, Train Accuracy: 0.5223, Val Loss: 1.4336, Val Accuracy: 0.5223 Epoch 2125/10000, Train Loss: 1.4202, Train Accuracy: 0.5346, Val Loss: 1.4335, Val Accuracy: 0.5179 Epoch 2126/10000, Train Loss: 1.4264, Train Accuracy: 0.5257, Val Loss: 1.4334, Val Accuracy: 0.5179 Epoch 2127/10000, Train Loss: 1.4198, Train Accuracy: 0.5312, Val Loss: 1.4333, Val Accuracy: 0.5179 Epoch 2128/10000, Train Loss: 1.4234, Train Accuracy: 0.5234, Val Loss: 1.4331, Val Accuracy: 0.5179 Epoch 2129/10000, Train Loss: 1.4234, Train Accuracy: 0.5022, Val Loss: 1.4330, Val Accuracy: 0.5179 Epoch 2130/10000, Train Loss: 1.4281, Train Accuracy: 0.5022, Val Loss: 1.4329, Val Accuracy: 0.5179 Epoch 2131/10000, Train Loss: 1.4242, Train Accuracy: 0.5167, Val Loss: 1.4328, Val Accuracy: 0.5179 Epoch 2132/10000, Train Loss: 1.4213, Train Accuracy: 0.5446, Val Loss: 1.4327, Val Accuracy: 0.5223 Epoch 2133/10000, Train Loss: 1.4278, Train Accuracy: 0.4978, Val Loss: 1.4326, Val Accuracy: 0.5223 Epoch 2134/10000, Train Loss: 1.4226, Train Accuracy: 0.5246, Val Loss: 1.4324, Val Accuracy: 0.5223 Epoch 2135/10000, Train Loss: 1.4274, Train Accuracy: 0.5045, Val Loss: 1.4323, Val Accuracy: 0.5179 Epoch 2136/10000, Train Loss: 1.4156, Train Accuracy: 0.5223, Val Loss: 1.4322, Val Accuracy: 0.5179 Epoch 2137/10000, Train Loss: 1.4204, Train Accuracy: 0.5279, Val Loss: 1.4321, Val Accuracy: 0.5179 Epoch 2138/10000, Train Loss: 1.4238, Train Accuracy: 0.5279, Val Loss: 1.4319, Val Accuracy: 0.5179 Epoch 2139/10000, Train Loss: 1.4278, Train Accuracy: 0.5145, Val Loss: 1.4318, Val Accuracy: 0.5223 Epoch 2140/10000, Train Loss: 1.4248, Train Accuracy: 0.5279, Val Loss: 1.4316, Val Accuracy: 0.5179 Epoch 2141/10000, Train Loss: 1.4282, Train Accuracy: 0.5145, Val Loss: 1.4315, Val Accuracy: 0.5179 Epoch 2142/10000, Train Loss: 1.4280, Train Accuracy: 0.5212, Val Loss: 1.4315, Val Accuracy: 0.5179 Epoch 2143/10000, Train Loss: 1.4209, Train Accuracy: 0.5246, Val Loss: 1.4314, Val Accuracy: 0.5134 Epoch 2144/10000, Train Loss: 1.4218, Train Accuracy: 0.5357, Val Loss: 1.4313, Val Accuracy: 0.5134 Epoch 2145/10000, Train Loss: 1.4169, Train Accuracy: 0.5279, Val Loss: 1.4312, Val Accuracy: 0.5134 Epoch 2146/10000, Train Loss: 1.4173, Train Accuracy: 0.5402, Val Loss: 1.4311, Val Accuracy: 0.5134 Epoch 2147/10000, Train Loss: 1.4282, Train Accuracy: 0.5056, Val Loss: 1.4310, Val Accuracy: 0.5134 Epoch 2148/10000, Train Loss: 1.4173, Train Accuracy: 0.5324, Val Loss: 1.4309, Val Accuracy: 0.5179 Epoch 2149/10000, Train Loss: 1.4224, Train Accuracy: 0.5312, Val Loss: 1.4307, Val Accuracy: 0.5134 Epoch 2150/10000, Train Loss: 1.4233, Train Accuracy: 0.5134, Val Loss: 1.4306, Val Accuracy: 0.5134 Epoch 2151/10000, Train Loss: 1.4214, Train Accuracy: 0.5246, Val Loss: 1.4305, Val Accuracy: 0.5134 Epoch 2152/10000, Train Loss: 1.4165, Train Accuracy: 0.5357, Val Loss: 1.4304, Val Accuracy: 0.5134 Epoch 2153/10000, Train Loss: 1.4162, Train Accuracy: 0.5257, Val Loss: 1.4303, Val Accuracy: 0.5134 Epoch 2154/10000, Train Loss: 1.4177, Train Accuracy: 0.5234, Val Loss: 1.4301, Val Accuracy: 0.5134 Epoch 2155/10000, Train Loss: 1.4209, Train Accuracy: 0.5134, Val Loss: 1.4300, Val Accuracy: 0.5134 Epoch 2156/10000, Train Loss: 1.4213, Train Accuracy: 0.5190, Val Loss: 1.4298, Val Accuracy: 0.5089 Epoch 2157/10000, Train Loss: 1.4121, Train Accuracy: 0.5368, Val Loss: 1.4297, Val Accuracy: 0.5089 Epoch 2158/10000, Train Loss: 1.4219, Train Accuracy: 0.5357, Val Loss: 1.4296, Val Accuracy: 0.5089 Epoch 2159/10000, Train Loss: 1.4318, Train Accuracy: 0.4978, Val Loss: 1.4295, Val Accuracy: 0.5089 Epoch 2160/10000, Train Loss: 1.4200, Train Accuracy: 0.5201, Val Loss: 1.4293, Val Accuracy: 0.5089 Epoch 2161/10000, Train Loss: 1.4220, Train Accuracy: 0.5145, Val Loss: 1.4291, Val Accuracy: 0.5089 Epoch 2162/10000, Train Loss: 1.4205, Train Accuracy: 0.5223, Val Loss: 1.4290, Val Accuracy: 0.5089 Epoch 2163/10000, Train Loss: 1.4164, Train Accuracy: 0.5335, Val Loss: 1.4287, Val Accuracy: 0.5089 Epoch 2164/10000, Train Loss: 1.4221, Train Accuracy: 0.5246, Val Loss: 1.4286, Val Accuracy: 0.5089 Epoch 2165/10000, Train Loss: 1.4147, Train Accuracy: 0.5190, Val Loss: 1.4285, Val Accuracy: 0.5089 Epoch 2166/10000, Train Loss: 1.4225, Train Accuracy: 0.5246, Val Loss: 1.4284, Val Accuracy: 0.5089 Epoch 2167/10000, Train Loss: 1.4165, Train Accuracy: 0.5357, Val Loss: 1.4284, Val Accuracy: 0.5089 Epoch 2168/10000, Train Loss: 1.4183, Train Accuracy: 0.5134, Val Loss: 1.4284, Val Accuracy: 0.5089 Epoch 2169/10000, Train Loss: 1.4142, Train Accuracy: 0.5469, Val Loss: 1.4283, Val Accuracy: 0.5089 Epoch 2170/10000, Train Loss: 1.4179, Train Accuracy: 0.5167, Val Loss: 1.4282, Val Accuracy: 0.5089 Epoch 2171/10000, Train Loss: 1.4160, Train Accuracy: 0.5190, Val Loss: 1.4280, Val Accuracy: 0.5089 Epoch 2172/10000, Train Loss: 1.4164, Train Accuracy: 0.5234, Val Loss: 1.4280, Val Accuracy: 0.5089 Epoch 2173/10000, Train Loss: 1.4142, Train Accuracy: 0.5368, Val Loss: 1.4278, Val Accuracy: 0.5089 Epoch 2174/10000, Train Loss: 1.4177, Train Accuracy: 0.5312, Val Loss: 1.4277, Val Accuracy: 0.5089 Epoch 2175/10000, Train Loss: 1.4176, Train Accuracy: 0.5212, Val Loss: 1.4276, Val Accuracy: 0.5089 Epoch 2176/10000, Train Loss: 1.4188, Train Accuracy: 0.5424, Val Loss: 1.4274, Val Accuracy: 0.5089 Epoch 2177/10000, Train Loss: 1.4146, Train Accuracy: 0.5257, Val Loss: 1.4273, Val Accuracy: 0.5089 Epoch 2178/10000, Train Loss: 1.4139, Train Accuracy: 0.5368, Val Loss: 1.4272, Val Accuracy: 0.5089 Epoch 2179/10000, Train Loss: 1.4190, Train Accuracy: 0.5134, Val Loss: 1.4271, Val Accuracy: 0.5089 Epoch 2180/10000, Train Loss: 1.4202, Train Accuracy: 0.5201, Val Loss: 1.4270, Val Accuracy: 0.5089 Epoch 2181/10000, Train Loss: 1.4175, Train Accuracy: 0.5223, Val Loss: 1.4269, Val Accuracy: 0.5089 Epoch 2182/10000, Train Loss: 1.4151, Train Accuracy: 0.5223, Val Loss: 1.4267, Val Accuracy: 0.5089 Epoch 2183/10000, Train Loss: 1.4169, Train Accuracy: 0.5201, Val Loss: 1.4267, Val Accuracy: 0.5089 Epoch 2184/10000, Train Loss: 1.4231, Train Accuracy: 0.5022, Val Loss: 1.4266, Val Accuracy: 0.5089 Epoch 2185/10000, Train Loss: 1.4130, Train Accuracy: 0.5234, Val Loss: 1.4264, Val Accuracy: 0.5089 Epoch 2186/10000, Train Loss: 1.4194, Train Accuracy: 0.5145, Val Loss: 1.4263, Val Accuracy: 0.5089 Epoch 2187/10000, Train Loss: 1.4159, Train Accuracy: 0.5502, Val Loss: 1.4262, Val Accuracy: 0.5089 Epoch 2188/10000, Train Loss: 1.4193, Train Accuracy: 0.5134, Val Loss: 1.4261, Val Accuracy: 0.5089 Epoch 2189/10000, Train Loss: 1.4167, Train Accuracy: 0.5190, Val Loss: 1.4260, Val Accuracy: 0.5089 Epoch 2190/10000, Train Loss: 1.4141, Train Accuracy: 0.5212, Val Loss: 1.4259, Val Accuracy: 0.5089 Epoch 2191/10000, Train Loss: 1.4211, Train Accuracy: 0.5167, Val Loss: 1.4257, Val Accuracy: 0.5089 Epoch 2192/10000, Train Loss: 1.4174, Train Accuracy: 0.5357, Val Loss: 1.4256, Val Accuracy: 0.5089 Epoch 2193/10000, Train Loss: 1.4167, Train Accuracy: 0.5223, Val Loss: 1.4255, Val Accuracy: 0.5089 Epoch 2194/10000, Train Loss: 1.4128, Train Accuracy: 0.5446, Val Loss: 1.4254, Val Accuracy: 0.5089 Epoch 2195/10000, Train Loss: 1.4191, Train Accuracy: 0.5379, Val Loss: 1.4253, Val Accuracy: 0.5089 Epoch 2196/10000, Train Loss: 1.4115, Train Accuracy: 0.5167, Val Loss: 1.4252, Val Accuracy: 0.5089 Epoch 2197/10000, Train Loss: 1.4110, Train Accuracy: 0.5469, Val Loss: 1.4251, Val Accuracy: 0.5089 Epoch 2198/10000, Train Loss: 1.4092, Train Accuracy: 0.5212, Val Loss: 1.4249, Val Accuracy: 0.5089 Epoch 2199/10000, Train Loss: 1.4051, Train Accuracy: 0.5502, Val Loss: 1.4249, Val Accuracy: 0.5089 Epoch 2200/10000, Train Loss: 1.4156, Train Accuracy: 0.5402, Val Loss: 1.4248, Val Accuracy: 0.5089 Epoch 2201/10000, Train Loss: 1.4110, Train Accuracy: 0.5391, Val Loss: 1.4246, Val Accuracy: 0.5089 Epoch 2202/10000, Train Loss: 1.4114, Train Accuracy: 0.5469, Val Loss: 1.4246, Val Accuracy: 0.5089 Epoch 2203/10000, Train Loss: 1.4162, Train Accuracy: 0.5301, Val Loss: 1.4245, Val Accuracy: 0.5089 Epoch 2204/10000, Train Loss: 1.4143, Train Accuracy: 0.5212, Val Loss: 1.4244, Val Accuracy: 0.5089 Epoch 2205/10000, Train Loss: 1.4113, Train Accuracy: 0.5368, Val Loss: 1.4242, Val Accuracy: 0.5089 Epoch 2206/10000, Train Loss: 1.4097, Train Accuracy: 0.5491, Val Loss: 1.4240, Val Accuracy: 0.5089 Epoch 2207/10000, Train Loss: 1.4107, Train Accuracy: 0.5413, Val Loss: 1.4239, Val Accuracy: 0.5089 Epoch 2208/10000, Train Loss: 1.4097, Train Accuracy: 0.5279, Val Loss: 1.4238, Val Accuracy: 0.5134 Epoch 2209/10000, Train Loss: 1.4177, Train Accuracy: 0.5246, Val Loss: 1.4237, Val Accuracy: 0.5134 Epoch 2210/10000, Train Loss: 1.4127, Train Accuracy: 0.5335, Val Loss: 1.4236, Val Accuracy: 0.5134 Epoch 2211/10000, Train Loss: 1.4126, Train Accuracy: 0.5469, Val Loss: 1.4234, Val Accuracy: 0.5089 Epoch 2212/10000, Train Loss: 1.4160, Train Accuracy: 0.5190, Val Loss: 1.4234, Val Accuracy: 0.5134 Epoch 2213/10000, Train Loss: 1.4122, Train Accuracy: 0.5424, Val Loss: 1.4232, Val Accuracy: 0.5134 Epoch 2214/10000, Train Loss: 1.4083, Train Accuracy: 0.5469, Val Loss: 1.4231, Val Accuracy: 0.5134 Epoch 2215/10000, Train Loss: 1.4096, Train Accuracy: 0.5391, Val Loss: 1.4230, Val Accuracy: 0.5134 Epoch 2216/10000, Train Loss: 1.4063, Train Accuracy: 0.5368, Val Loss: 1.4228, Val Accuracy: 0.5134 Epoch 2217/10000, Train Loss: 1.4192, Train Accuracy: 0.5257, Val Loss: 1.4227, Val Accuracy: 0.5134 Epoch 2218/10000, Train Loss: 1.4060, Train Accuracy: 0.5446, Val Loss: 1.4226, Val Accuracy: 0.5134 Epoch 2219/10000, Train Loss: 1.4128, Train Accuracy: 0.5469, Val Loss: 1.4225, Val Accuracy: 0.5134 Epoch 2220/10000, Train Loss: 1.4101, Train Accuracy: 0.5357, Val Loss: 1.4224, Val Accuracy: 0.5134 Epoch 2221/10000, Train Loss: 1.4100, Train Accuracy: 0.5502, Val Loss: 1.4223, Val Accuracy: 0.5134 Epoch 2222/10000, Train Loss: 1.4128, Train Accuracy: 0.5257, Val Loss: 1.4222, Val Accuracy: 0.5179 Epoch 2223/10000, Train Loss: 1.4086, Train Accuracy: 0.5335, Val Loss: 1.4221, Val Accuracy: 0.5179 Epoch 2224/10000, Train Loss: 1.4125, Train Accuracy: 0.5312, Val Loss: 1.4219, Val Accuracy: 0.5179 Epoch 2225/10000, Train Loss: 1.4091, Train Accuracy: 0.5491, Val Loss: 1.4218, Val Accuracy: 0.5179 Epoch 2226/10000, Train Loss: 1.4102, Train Accuracy: 0.5469, Val Loss: 1.4217, Val Accuracy: 0.5179 Epoch 2227/10000, Train Loss: 1.4094, Train Accuracy: 0.5357, Val Loss: 1.4216, Val Accuracy: 0.5179 Epoch 2228/10000, Train Loss: 1.4113, Train Accuracy: 0.5536, Val Loss: 1.4214, Val Accuracy: 0.5179 Epoch 2229/10000, Train Loss: 1.4085, Train Accuracy: 0.5469, Val Loss: 1.4214, Val Accuracy: 0.5179 Epoch 2230/10000, Train Loss: 1.4067, Train Accuracy: 0.5413, Val Loss: 1.4212, Val Accuracy: 0.5179 Epoch 2231/10000, Train Loss: 1.4017, Train Accuracy: 0.5357, Val Loss: 1.4211, Val Accuracy: 0.5179 Epoch 2232/10000, Train Loss: 1.4046, Train Accuracy: 0.5469, Val Loss: 1.4210, Val Accuracy: 0.5179 Epoch 2233/10000, Train Loss: 1.4000, Train Accuracy: 0.5569, Val Loss: 1.4209, Val Accuracy: 0.5179 Epoch 2234/10000, Train Loss: 1.4087, Train Accuracy: 0.5413, Val Loss: 1.4208, Val Accuracy: 0.5179 Epoch 2235/10000, Train Loss: 1.4028, Train Accuracy: 0.5446, Val Loss: 1.4206, Val Accuracy: 0.5179 Epoch 2236/10000, Train Loss: 1.4113, Train Accuracy: 0.5167, Val Loss: 1.4206, Val Accuracy: 0.5179 Epoch 2237/10000, Train Loss: 1.4072, Train Accuracy: 0.5290, Val Loss: 1.4205, Val Accuracy: 0.5179 Epoch 2238/10000, Train Loss: 1.4129, Train Accuracy: 0.5324, Val Loss: 1.4204, Val Accuracy: 0.5179 Epoch 2239/10000, Train Loss: 1.4097, Train Accuracy: 0.5513, Val Loss: 1.4203, Val Accuracy: 0.5223 Epoch 2240/10000, Train Loss: 1.4100, Train Accuracy: 0.5368, Val Loss: 1.4201, Val Accuracy: 0.5179 Epoch 2241/10000, Train Loss: 1.4111, Train Accuracy: 0.5312, Val Loss: 1.4200, Val Accuracy: 0.5179 Epoch 2242/10000, Train Loss: 1.4173, Train Accuracy: 0.5134, Val Loss: 1.4199, Val Accuracy: 0.5223 Epoch 2243/10000, Train Loss: 1.4091, Train Accuracy: 0.5435, Val Loss: 1.4198, Val Accuracy: 0.5223 Epoch 2244/10000, Train Loss: 1.4068, Train Accuracy: 0.5491, Val Loss: 1.4196, Val Accuracy: 0.5223 Epoch 2245/10000, Train Loss: 1.4105, Train Accuracy: 0.5446, Val Loss: 1.4195, Val Accuracy: 0.5223 Epoch 2246/10000, Train Loss: 1.4092, Train Accuracy: 0.5335, Val Loss: 1.4195, Val Accuracy: 0.5223 Epoch 2247/10000, Train Loss: 1.4067, Train Accuracy: 0.5234, Val Loss: 1.4194, Val Accuracy: 0.5223 Epoch 2248/10000, Train Loss: 1.4096, Train Accuracy: 0.5223, Val Loss: 1.4192, Val Accuracy: 0.5223 Epoch 2249/10000, Train Loss: 1.4071, Train Accuracy: 0.5435, Val Loss: 1.4192, Val Accuracy: 0.5268 Epoch 2250/10000, Train Loss: 1.4089, Train Accuracy: 0.5536, Val Loss: 1.4191, Val Accuracy: 0.5268 Epoch 2251/10000, Train Loss: 1.4079, Train Accuracy: 0.5402, Val Loss: 1.4190, Val Accuracy: 0.5268 Epoch 2252/10000, Train Loss: 1.4069, Train Accuracy: 0.5335, Val Loss: 1.4189, Val Accuracy: 0.5268 Epoch 2253/10000, Train Loss: 1.4007, Train Accuracy: 0.5714, Val Loss: 1.4188, Val Accuracy: 0.5268 Epoch 2254/10000, Train Loss: 1.4027, Train Accuracy: 0.5502, Val Loss: 1.4187, Val Accuracy: 0.5223 Epoch 2255/10000, Train Loss: 1.4031, Train Accuracy: 0.5525, Val Loss: 1.4186, Val Accuracy: 0.5223 Epoch 2256/10000, Train Loss: 1.4107, Train Accuracy: 0.5246, Val Loss: 1.4185, Val Accuracy: 0.5223 Epoch 2257/10000, Train Loss: 1.4055, Train Accuracy: 0.5290, Val Loss: 1.4184, Val Accuracy: 0.5223 Epoch 2258/10000, Train Loss: 1.4054, Train Accuracy: 0.5536, Val Loss: 1.4183, Val Accuracy: 0.5223 Epoch 2259/10000, Train Loss: 1.4022, Train Accuracy: 0.5480, Val Loss: 1.4181, Val Accuracy: 0.5223 Epoch 2260/10000, Train Loss: 1.4031, Train Accuracy: 0.5458, Val Loss: 1.4180, Val Accuracy: 0.5223 Epoch 2261/10000, Train Loss: 1.4087, Train Accuracy: 0.5357, Val Loss: 1.4179, Val Accuracy: 0.5223 Epoch 2262/10000, Train Loss: 1.4057, Train Accuracy: 0.5391, Val Loss: 1.4178, Val Accuracy: 0.5223 Epoch 2263/10000, Train Loss: 1.4061, Train Accuracy: 0.5424, Val Loss: 1.4177, Val Accuracy: 0.5223 Epoch 2264/10000, Train Loss: 1.4128, Train Accuracy: 0.5402, Val Loss: 1.4176, Val Accuracy: 0.5223 Epoch 2265/10000, Train Loss: 1.4019, Train Accuracy: 0.5614, Val Loss: 1.4174, Val Accuracy: 0.5223 Epoch 2266/10000, Train Loss: 1.4095, Train Accuracy: 0.5246, Val Loss: 1.4173, Val Accuracy: 0.5223 Epoch 2267/10000, Train Loss: 1.4049, Train Accuracy: 0.5402, Val Loss: 1.4172, Val Accuracy: 0.5223 Epoch 2268/10000, Train Loss: 1.4023, Train Accuracy: 0.5312, Val Loss: 1.4171, Val Accuracy: 0.5223 Epoch 2269/10000, Train Loss: 1.4022, Train Accuracy: 0.5513, Val Loss: 1.4170, Val Accuracy: 0.5223 Epoch 2270/10000, Train Loss: 1.3931, Train Accuracy: 0.5636, Val Loss: 1.4168, Val Accuracy: 0.5223 Epoch 2271/10000, Train Loss: 1.4049, Train Accuracy: 0.5446, Val Loss: 1.4167, Val Accuracy: 0.5223 Epoch 2272/10000, Train Loss: 1.4039, Train Accuracy: 0.5346, Val Loss: 1.4166, Val Accuracy: 0.5223 Epoch 2273/10000, Train Loss: 1.4001, Train Accuracy: 0.5558, Val Loss: 1.4165, Val Accuracy: 0.5223 Epoch 2274/10000, Train Loss: 1.3998, Train Accuracy: 0.5603, Val Loss: 1.4164, Val Accuracy: 0.5223 Epoch 2275/10000, Train Loss: 1.4015, Train Accuracy: 0.5458, Val Loss: 1.4163, Val Accuracy: 0.5223 Epoch 2276/10000, Train Loss: 1.3956, Train Accuracy: 0.5525, Val Loss: 1.4162, Val Accuracy: 0.5223 Epoch 2277/10000, Train Loss: 1.3967, Train Accuracy: 0.5435, Val Loss: 1.4161, Val Accuracy: 0.5223 Epoch 2278/10000, Train Loss: 1.4018, Train Accuracy: 0.5357, Val Loss: 1.4160, Val Accuracy: 0.5223 Epoch 2279/10000, Train Loss: 1.3967, Train Accuracy: 0.5513, Val Loss: 1.4159, Val Accuracy: 0.5223 Epoch 2280/10000, Train Loss: 1.4043, Train Accuracy: 0.5391, Val Loss: 1.4158, Val Accuracy: 0.5223 Epoch 2281/10000, Train Loss: 1.4013, Train Accuracy: 0.5357, Val Loss: 1.4157, Val Accuracy: 0.5223 Epoch 2282/10000, Train Loss: 1.4062, Train Accuracy: 0.5513, Val Loss: 1.4156, Val Accuracy: 0.5223 Epoch 2283/10000, Train Loss: 1.3999, Train Accuracy: 0.5502, Val Loss: 1.4155, Val Accuracy: 0.5223 Epoch 2284/10000, Train Loss: 1.4006, Train Accuracy: 0.5379, Val Loss: 1.4154, Val Accuracy: 0.5268 Epoch 2285/10000, Train Loss: 1.4037, Train Accuracy: 0.5491, Val Loss: 1.4152, Val Accuracy: 0.5268 Epoch 2286/10000, Train Loss: 1.3997, Train Accuracy: 0.5547, Val Loss: 1.4151, Val Accuracy: 0.5268 Epoch 2287/10000, Train Loss: 1.4041, Train Accuracy: 0.5402, Val Loss: 1.4150, Val Accuracy: 0.5268 Epoch 2288/10000, Train Loss: 1.4025, Train Accuracy: 0.5424, Val Loss: 1.4149, Val Accuracy: 0.5268 Epoch 2289/10000, Train Loss: 1.3994, Train Accuracy: 0.5424, Val Loss: 1.4147, Val Accuracy: 0.5268 Epoch 2290/10000, Train Loss: 1.4041, Train Accuracy: 0.5379, Val Loss: 1.4146, Val Accuracy: 0.5268 Epoch 2291/10000, Train Loss: 1.4021, Train Accuracy: 0.5435, Val Loss: 1.4145, Val Accuracy: 0.5268 Epoch 2292/10000, Train Loss: 1.3992, Train Accuracy: 0.5480, Val Loss: 1.4144, Val Accuracy: 0.5268 Epoch 2293/10000, Train Loss: 1.4000, Train Accuracy: 0.5491, Val Loss: 1.4143, Val Accuracy: 0.5268 Epoch 2294/10000, Train Loss: 1.3991, Train Accuracy: 0.5502, Val Loss: 1.4142, Val Accuracy: 0.5268 Epoch 2295/10000, Train Loss: 1.3966, Train Accuracy: 0.5592, Val Loss: 1.4141, Val Accuracy: 0.5268 Epoch 2296/10000, Train Loss: 1.3966, Train Accuracy: 0.5513, Val Loss: 1.4140, Val Accuracy: 0.5268 Epoch 2297/10000, Train Loss: 1.3994, Train Accuracy: 0.5480, Val Loss: 1.4139, Val Accuracy: 0.5268 Epoch 2298/10000, Train Loss: 1.3950, Train Accuracy: 0.5513, Val Loss: 1.4138, Val Accuracy: 0.5268 Epoch 2299/10000, Train Loss: 1.4012, Train Accuracy: 0.5368, Val Loss: 1.4137, Val Accuracy: 0.5268 Epoch 2300/10000, Train Loss: 1.3978, Train Accuracy: 0.5346, Val Loss: 1.4135, Val Accuracy: 0.5223 Epoch 2301/10000, Train Loss: 1.3956, Train Accuracy: 0.5446, Val Loss: 1.4134, Val Accuracy: 0.5223 Epoch 2302/10000, Train Loss: 1.4017, Train Accuracy: 0.5402, Val Loss: 1.4132, Val Accuracy: 0.5223 Epoch 2303/10000, Train Loss: 1.4044, Train Accuracy: 0.5469, Val Loss: 1.4132, Val Accuracy: 0.5223 Epoch 2304/10000, Train Loss: 1.3929, Train Accuracy: 0.5480, Val Loss: 1.4130, Val Accuracy: 0.5223 Epoch 2305/10000, Train Loss: 1.4012, Train Accuracy: 0.5357, Val Loss: 1.4129, Val Accuracy: 0.5223 Epoch 2306/10000, Train Loss: 1.4008, Train Accuracy: 0.5502, Val Loss: 1.4128, Val Accuracy: 0.5223 Epoch 2307/10000, Train Loss: 1.3924, Train Accuracy: 0.5703, Val Loss: 1.4127, Val Accuracy: 0.5223 Epoch 2308/10000, Train Loss: 1.3967, Train Accuracy: 0.5469, Val Loss: 1.4126, Val Accuracy: 0.5223 Epoch 2309/10000, Train Loss: 1.4050, Train Accuracy: 0.5446, Val Loss: 1.4125, Val Accuracy: 0.5223 Epoch 2310/10000, Train Loss: 1.3920, Train Accuracy: 0.5759, Val Loss: 1.4123, Val Accuracy: 0.5223 Epoch 2311/10000, Train Loss: 1.3962, Train Accuracy: 0.5435, Val Loss: 1.4122, Val Accuracy: 0.5223 Epoch 2312/10000, Train Loss: 1.3972, Train Accuracy: 0.5424, Val Loss: 1.4121, Val Accuracy: 0.5223 Epoch 2313/10000, Train Loss: 1.3970, Train Accuracy: 0.5547, Val Loss: 1.4120, Val Accuracy: 0.5223 Epoch 2314/10000, Train Loss: 1.3960, Train Accuracy: 0.5324, Val Loss: 1.4119, Val Accuracy: 0.5223 Epoch 2315/10000, Train Loss: 1.4021, Train Accuracy: 0.5402, Val Loss: 1.4118, Val Accuracy: 0.5223 Epoch 2316/10000, Train Loss: 1.3985, Train Accuracy: 0.5525, Val Loss: 1.4117, Val Accuracy: 0.5223 Epoch 2317/10000, Train Loss: 1.3985, Train Accuracy: 0.5368, Val Loss: 1.4116, Val Accuracy: 0.5223 Epoch 2318/10000, Train Loss: 1.4020, Train Accuracy: 0.5513, Val Loss: 1.4115, Val Accuracy: 0.5223 Epoch 2319/10000, Train Loss: 1.3921, Train Accuracy: 0.5513, Val Loss: 1.4114, Val Accuracy: 0.5223 Epoch 2320/10000, Train Loss: 1.3977, Train Accuracy: 0.5525, Val Loss: 1.4113, Val Accuracy: 0.5223 Epoch 2321/10000, Train Loss: 1.3996, Train Accuracy: 0.5480, Val Loss: 1.4112, Val Accuracy: 0.5223 Epoch 2322/10000, Train Loss: 1.3956, Train Accuracy: 0.5435, Val Loss: 1.4110, Val Accuracy: 0.5223 Epoch 2323/10000, Train Loss: 1.4021, Train Accuracy: 0.5357, Val Loss: 1.4109, Val Accuracy: 0.5223 Epoch 2324/10000, Train Loss: 1.3950, Train Accuracy: 0.5480, Val Loss: 1.4109, Val Accuracy: 0.5223 Epoch 2325/10000, Train Loss: 1.3962, Train Accuracy: 0.5525, Val Loss: 1.4108, Val Accuracy: 0.5223 Epoch 2326/10000, Train Loss: 1.3981, Train Accuracy: 0.5458, Val Loss: 1.4107, Val Accuracy: 0.5223 Epoch 2327/10000, Train Loss: 1.3967, Train Accuracy: 0.5536, Val Loss: 1.4106, Val Accuracy: 0.5223 Epoch 2328/10000, Train Loss: 1.3994, Train Accuracy: 0.5402, Val Loss: 1.4104, Val Accuracy: 0.5223 Epoch 2329/10000, Train Loss: 1.3929, Train Accuracy: 0.5547, Val Loss: 1.4103, Val Accuracy: 0.5223 Epoch 2330/10000, Train Loss: 1.3975, Train Accuracy: 0.5491, Val Loss: 1.4102, Val Accuracy: 0.5223 Epoch 2331/10000, Train Loss: 1.3944, Train Accuracy: 0.5558, Val Loss: 1.4101, Val Accuracy: 0.5223 Epoch 2332/10000, Train Loss: 1.3926, Train Accuracy: 0.5413, Val Loss: 1.4100, Val Accuracy: 0.5179 Epoch 2333/10000, Train Loss: 1.3985, Train Accuracy: 0.5435, Val Loss: 1.4099, Val Accuracy: 0.5179 Epoch 2334/10000, Train Loss: 1.4000, Train Accuracy: 0.5212, Val Loss: 1.4098, Val Accuracy: 0.5134 Epoch 2335/10000, Train Loss: 1.3984, Train Accuracy: 0.5525, Val Loss: 1.4097, Val Accuracy: 0.5134 Epoch 2336/10000, Train Loss: 1.3973, Train Accuracy: 0.5458, Val Loss: 1.4095, Val Accuracy: 0.5134 Epoch 2337/10000, Train Loss: 1.3941, Train Accuracy: 0.5458, Val Loss: 1.4094, Val Accuracy: 0.5134 Epoch 2338/10000, Train Loss: 1.3924, Train Accuracy: 0.5536, Val Loss: 1.4093, Val Accuracy: 0.5134 Epoch 2339/10000, Train Loss: 1.3941, Train Accuracy: 0.5513, Val Loss: 1.4092, Val Accuracy: 0.5134 Epoch 2340/10000, Train Loss: 1.3976, Train Accuracy: 0.5558, Val Loss: 1.4091, Val Accuracy: 0.5134 Epoch 2341/10000, Train Loss: 1.3972, Train Accuracy: 0.5491, Val Loss: 1.4090, Val Accuracy: 0.5179 Epoch 2342/10000, Train Loss: 1.3932, Train Accuracy: 0.5402, Val Loss: 1.4090, Val Accuracy: 0.5179 Epoch 2343/10000, Train Loss: 1.3868, Train Accuracy: 0.5636, Val Loss: 1.4088, Val Accuracy: 0.5134 Epoch 2344/10000, Train Loss: 1.3952, Train Accuracy: 0.5525, Val Loss: 1.4087, Val Accuracy: 0.5134 Epoch 2345/10000, Train Loss: 1.3897, Train Accuracy: 0.5725, Val Loss: 1.4086, Val Accuracy: 0.5134 Epoch 2346/10000, Train Loss: 1.3940, Train Accuracy: 0.5458, Val Loss: 1.4085, Val Accuracy: 0.5134 Epoch 2347/10000, Train Loss: 1.3944, Train Accuracy: 0.5536, Val Loss: 1.4084, Val Accuracy: 0.5134 Epoch 2348/10000, Train Loss: 1.3879, Train Accuracy: 0.5569, Val Loss: 1.4083, Val Accuracy: 0.5134 Epoch 2349/10000, Train Loss: 1.3910, Train Accuracy: 0.5580, Val Loss: 1.4082, Val Accuracy: 0.5089 Epoch 2350/10000, Train Loss: 1.3921, Train Accuracy: 0.5446, Val Loss: 1.4081, Val Accuracy: 0.5089 Epoch 2351/10000, Train Loss: 1.3940, Train Accuracy: 0.5580, Val Loss: 1.4080, Val Accuracy: 0.5089 Epoch 2352/10000, Train Loss: 1.3907, Train Accuracy: 0.5603, Val Loss: 1.4079, Val Accuracy: 0.5089 Epoch 2353/10000, Train Loss: 1.3944, Train Accuracy: 0.5558, Val Loss: 1.4078, Val Accuracy: 0.5089 Epoch 2354/10000, Train Loss: 1.3939, Train Accuracy: 0.5391, Val Loss: 1.4076, Val Accuracy: 0.5089 Epoch 2355/10000, Train Loss: 1.3976, Train Accuracy: 0.5469, Val Loss: 1.4075, Val Accuracy: 0.5089 Epoch 2356/10000, Train Loss: 1.4003, Train Accuracy: 0.5502, Val Loss: 1.4074, Val Accuracy: 0.5134 Epoch 2357/10000, Train Loss: 1.3941, Train Accuracy: 0.5502, Val Loss: 1.4073, Val Accuracy: 0.5134 Epoch 2358/10000, Train Loss: 1.3932, Train Accuracy: 0.5592, Val Loss: 1.4072, Val Accuracy: 0.5134 Epoch 2359/10000, Train Loss: 1.3868, Train Accuracy: 0.5815, Val Loss: 1.4071, Val Accuracy: 0.5134 Epoch 2360/10000, Train Loss: 1.3910, Train Accuracy: 0.5502, Val Loss: 1.4069, Val Accuracy: 0.5134 Epoch 2361/10000, Train Loss: 1.3927, Train Accuracy: 0.5458, Val Loss: 1.4068, Val Accuracy: 0.5134 Epoch 2362/10000, Train Loss: 1.3891, Train Accuracy: 0.5670, Val Loss: 1.4067, Val Accuracy: 0.5134 Epoch 2363/10000, Train Loss: 1.3862, Train Accuracy: 0.5569, Val Loss: 1.4066, Val Accuracy: 0.5134 Epoch 2364/10000, Train Loss: 1.3862, Train Accuracy: 0.5625, Val Loss: 1.4065, Val Accuracy: 0.5089 Epoch 2365/10000, Train Loss: 1.3891, Train Accuracy: 0.5580, Val Loss: 1.4063, Val Accuracy: 0.5045 Epoch 2366/10000, Train Loss: 1.3886, Train Accuracy: 0.5692, Val Loss: 1.4063, Val Accuracy: 0.5045 Epoch 2367/10000, Train Loss: 1.3953, Train Accuracy: 0.5413, Val Loss: 1.4062, Val Accuracy: 0.5045 Epoch 2368/10000, Train Loss: 1.3889, Train Accuracy: 0.5692, Val Loss: 1.4061, Val Accuracy: 0.5089 Epoch 2369/10000, Train Loss: 1.3894, Train Accuracy: 0.5547, Val Loss: 1.4060, Val Accuracy: 0.5045 Epoch 2370/10000, Train Loss: 1.3944, Train Accuracy: 0.5413, Val Loss: 1.4059, Val Accuracy: 0.5045 Epoch 2371/10000, Train Loss: 1.3950, Train Accuracy: 0.5312, Val Loss: 1.4058, Val Accuracy: 0.5045 Epoch 2372/10000, Train Loss: 1.3910, Train Accuracy: 0.5647, Val Loss: 1.4058, Val Accuracy: 0.5045 Epoch 2373/10000, Train Loss: 1.3917, Train Accuracy: 0.5625, Val Loss: 1.4056, Val Accuracy: 0.5045 Epoch 2374/10000, Train Loss: 1.3859, Train Accuracy: 0.5681, Val Loss: 1.4055, Val Accuracy: 0.5089 Epoch 2375/10000, Train Loss: 1.3797, Train Accuracy: 0.5748, Val Loss: 1.4055, Val Accuracy: 0.5089 Epoch 2376/10000, Train Loss: 1.3888, Train Accuracy: 0.5446, Val Loss: 1.4054, Val Accuracy: 0.5089 Epoch 2377/10000, Train Loss: 1.3811, Train Accuracy: 0.5815, Val Loss: 1.4052, Val Accuracy: 0.5089 Epoch 2378/10000, Train Loss: 1.3922, Train Accuracy: 0.5536, Val Loss: 1.4051, Val Accuracy: 0.5089 Epoch 2379/10000, Train Loss: 1.3906, Train Accuracy: 0.5592, Val Loss: 1.4050, Val Accuracy: 0.5089 Epoch 2380/10000, Train Loss: 1.3883, Train Accuracy: 0.5547, Val Loss: 1.4050, Val Accuracy: 0.5089 Epoch 2381/10000, Train Loss: 1.3904, Train Accuracy: 0.5536, Val Loss: 1.4048, Val Accuracy: 0.5089 Epoch 2382/10000, Train Loss: 1.3905, Train Accuracy: 0.5391, Val Loss: 1.4048, Val Accuracy: 0.5089 Epoch 2383/10000, Train Loss: 1.3840, Train Accuracy: 0.5670, Val Loss: 1.4047, Val Accuracy: 0.5089 Epoch 2384/10000, Train Loss: 1.3876, Train Accuracy: 0.5536, Val Loss: 1.4046, Val Accuracy: 0.5089 Epoch 2385/10000, Train Loss: 1.3918, Train Accuracy: 0.5480, Val Loss: 1.4045, Val Accuracy: 0.5089 Epoch 2386/10000, Train Loss: 1.3849, Train Accuracy: 0.5759, Val Loss: 1.4044, Val Accuracy: 0.5089 Epoch 2387/10000, Train Loss: 1.3834, Train Accuracy: 0.5681, Val Loss: 1.4042, Val Accuracy: 0.5089 Epoch 2388/10000, Train Loss: 1.3871, Train Accuracy: 0.5424, Val Loss: 1.4041, Val Accuracy: 0.5089 Epoch 2389/10000, Train Loss: 1.3925, Train Accuracy: 0.5491, Val Loss: 1.4040, Val Accuracy: 0.5089 Epoch 2390/10000, Train Loss: 1.3878, Train Accuracy: 0.5480, Val Loss: 1.4039, Val Accuracy: 0.5089 Epoch 2391/10000, Train Loss: 1.3863, Train Accuracy: 0.5391, Val Loss: 1.4038, Val Accuracy: 0.5089 Epoch 2392/10000, Train Loss: 1.3851, Train Accuracy: 0.5647, Val Loss: 1.4037, Val Accuracy: 0.5089 Epoch 2393/10000, Train Loss: 1.3816, Train Accuracy: 0.5703, Val Loss: 1.4036, Val Accuracy: 0.5089 Epoch 2394/10000, Train Loss: 1.3867, Train Accuracy: 0.5469, Val Loss: 1.4035, Val Accuracy: 0.5089 Epoch 2395/10000, Train Loss: 1.3942, Train Accuracy: 0.5413, Val Loss: 1.4034, Val Accuracy: 0.5134 Epoch 2396/10000, Train Loss: 1.3774, Train Accuracy: 0.5748, Val Loss: 1.4033, Val Accuracy: 0.5134 Epoch 2397/10000, Train Loss: 1.3892, Train Accuracy: 0.5547, Val Loss: 1.4032, Val Accuracy: 0.5134 Epoch 2398/10000, Train Loss: 1.3843, Train Accuracy: 0.5547, Val Loss: 1.4031, Val Accuracy: 0.5134 Epoch 2399/10000, Train Loss: 1.3772, Train Accuracy: 0.5714, Val Loss: 1.4030, Val Accuracy: 0.5134 Epoch 2400/10000, Train Loss: 1.3863, Train Accuracy: 0.5737, Val Loss: 1.4029, Val Accuracy: 0.5134 Epoch 2401/10000, Train Loss: 1.3850, Train Accuracy: 0.5536, Val Loss: 1.4028, Val Accuracy: 0.5134 Epoch 2402/10000, Train Loss: 1.3859, Train Accuracy: 0.5580, Val Loss: 1.4027, Val Accuracy: 0.5134 Epoch 2403/10000, Train Loss: 1.3846, Train Accuracy: 0.5558, Val Loss: 1.4026, Val Accuracy: 0.5134 Epoch 2404/10000, Train Loss: 1.3855, Train Accuracy: 0.5625, Val Loss: 1.4024, Val Accuracy: 0.5134 Epoch 2405/10000, Train Loss: 1.3863, Train Accuracy: 0.5592, Val Loss: 1.4023, Val Accuracy: 0.5134 Epoch 2406/10000, Train Loss: 1.3900, Train Accuracy: 0.5592, Val Loss: 1.4022, Val Accuracy: 0.5134 Epoch 2407/10000, Train Loss: 1.3830, Train Accuracy: 0.5670, Val Loss: 1.4021, Val Accuracy: 0.5134 Epoch 2408/10000, Train Loss: 1.3795, Train Accuracy: 0.5848, Val Loss: 1.4020, Val Accuracy: 0.5134 Epoch 2409/10000, Train Loss: 1.3832, Train Accuracy: 0.5681, Val Loss: 1.4019, Val Accuracy: 0.5134 Epoch 2410/10000, Train Loss: 1.3790, Train Accuracy: 0.5681, Val Loss: 1.4018, Val Accuracy: 0.5134 Epoch 2411/10000, Train Loss: 1.3844, Train Accuracy: 0.5513, Val Loss: 1.4016, Val Accuracy: 0.5134 Epoch 2412/10000, Train Loss: 1.3926, Train Accuracy: 0.5458, Val Loss: 1.4016, Val Accuracy: 0.5134 Epoch 2413/10000, Train Loss: 1.3803, Train Accuracy: 0.5658, Val Loss: 1.4015, Val Accuracy: 0.5134 Epoch 2414/10000, Train Loss: 1.3765, Train Accuracy: 0.5703, Val Loss: 1.4014, Val Accuracy: 0.5134 Epoch 2415/10000, Train Loss: 1.3766, Train Accuracy: 0.5781, Val Loss: 1.4013, Val Accuracy: 0.5134 Epoch 2416/10000, Train Loss: 1.3820, Train Accuracy: 0.5636, Val Loss: 1.4012, Val Accuracy: 0.5134 Epoch 2417/10000, Train Loss: 1.3817, Train Accuracy: 0.5670, Val Loss: 1.4011, Val Accuracy: 0.5134 Epoch 2418/10000, Train Loss: 1.3809, Train Accuracy: 0.5670, Val Loss: 1.4009, Val Accuracy: 0.5134 Epoch 2419/10000, Train Loss: 1.3814, Train Accuracy: 0.5670, Val Loss: 1.4008, Val Accuracy: 0.5134 Epoch 2420/10000, Train Loss: 1.3876, Train Accuracy: 0.5513, Val Loss: 1.4007, Val Accuracy: 0.5134 Epoch 2421/10000, Train Loss: 1.3839, Train Accuracy: 0.5569, Val Loss: 1.4006, Val Accuracy: 0.5134 Epoch 2422/10000, Train Loss: 1.3817, Train Accuracy: 0.5603, Val Loss: 1.4005, Val Accuracy: 0.5134 Epoch 2423/10000, Train Loss: 1.3800, Train Accuracy: 0.5703, Val Loss: 1.4004, Val Accuracy: 0.5134 Epoch 2424/10000, Train Loss: 1.3721, Train Accuracy: 0.5737, Val Loss: 1.4003, Val Accuracy: 0.5134 Epoch 2425/10000, Train Loss: 1.3833, Train Accuracy: 0.5580, Val Loss: 1.4002, Val Accuracy: 0.5134 Epoch 2426/10000, Train Loss: 1.3818, Train Accuracy: 0.5681, Val Loss: 1.4001, Val Accuracy: 0.5134 Epoch 2427/10000, Train Loss: 1.3828, Train Accuracy: 0.5614, Val Loss: 1.4000, Val Accuracy: 0.5134 Epoch 2428/10000, Train Loss: 1.3871, Train Accuracy: 0.5737, Val Loss: 1.3999, Val Accuracy: 0.5134 Epoch 2429/10000, Train Loss: 1.3806, Train Accuracy: 0.5603, Val Loss: 1.3998, Val Accuracy: 0.5134 Epoch 2430/10000, Train Loss: 1.3854, Train Accuracy: 0.5737, Val Loss: 1.3997, Val Accuracy: 0.5134 Epoch 2431/10000, Train Loss: 1.3819, Train Accuracy: 0.5569, Val Loss: 1.3997, Val Accuracy: 0.5134 Epoch 2432/10000, Train Loss: 1.3856, Train Accuracy: 0.5312, Val Loss: 1.3996, Val Accuracy: 0.5134 Epoch 2433/10000, Train Loss: 1.3828, Train Accuracy: 0.5703, Val Loss: 1.3995, Val Accuracy: 0.5134 Epoch 2434/10000, Train Loss: 1.3790, Train Accuracy: 0.5692, Val Loss: 1.3994, Val Accuracy: 0.5134 Epoch 2435/10000, Train Loss: 1.3761, Train Accuracy: 0.5558, Val Loss: 1.3993, Val Accuracy: 0.5134 Epoch 2436/10000, Train Loss: 1.3749, Train Accuracy: 0.5859, Val Loss: 1.3991, Val Accuracy: 0.5134 Epoch 2437/10000, Train Loss: 1.3844, Train Accuracy: 0.5491, Val Loss: 1.3990, Val Accuracy: 0.5134 Epoch 2438/10000, Train Loss: 1.3723, Train Accuracy: 0.5770, Val Loss: 1.3989, Val Accuracy: 0.5134 Epoch 2439/10000, Train Loss: 1.3813, Train Accuracy: 0.5569, Val Loss: 1.3988, Val Accuracy: 0.5134 Epoch 2440/10000, Train Loss: 1.3837, Train Accuracy: 0.5748, Val Loss: 1.3987, Val Accuracy: 0.5134 Epoch 2441/10000, Train Loss: 1.3798, Train Accuracy: 0.5636, Val Loss: 1.3987, Val Accuracy: 0.5134 Epoch 2442/10000, Train Loss: 1.3791, Train Accuracy: 0.5792, Val Loss: 1.3986, Val Accuracy: 0.5134 Epoch 2443/10000, Train Loss: 1.3810, Train Accuracy: 0.5502, Val Loss: 1.3985, Val Accuracy: 0.5134 Epoch 2444/10000, Train Loss: 1.3748, Train Accuracy: 0.5759, Val Loss: 1.3984, Val Accuracy: 0.5134 Epoch 2445/10000, Train Loss: 1.3758, Train Accuracy: 0.5748, Val Loss: 1.3983, Val Accuracy: 0.5134 Epoch 2446/10000, Train Loss: 1.3744, Train Accuracy: 0.5714, Val Loss: 1.3982, Val Accuracy: 0.5134 Epoch 2447/10000, Train Loss: 1.3813, Train Accuracy: 0.5636, Val Loss: 1.3981, Val Accuracy: 0.5134 Epoch 2448/10000, Train Loss: 1.3781, Train Accuracy: 0.5603, Val Loss: 1.3980, Val Accuracy: 0.5134 Epoch 2449/10000, Train Loss: 1.3815, Train Accuracy: 0.5469, Val Loss: 1.3979, Val Accuracy: 0.5134 Epoch 2450/10000, Train Loss: 1.3733, Train Accuracy: 0.5792, Val Loss: 1.3979, Val Accuracy: 0.5179 Epoch 2451/10000, Train Loss: 1.3800, Train Accuracy: 0.5580, Val Loss: 1.3977, Val Accuracy: 0.5179 Epoch 2452/10000, Train Loss: 1.3806, Train Accuracy: 0.5759, Val Loss: 1.3976, Val Accuracy: 0.5179 Epoch 2453/10000, Train Loss: 1.3830, Train Accuracy: 0.5435, Val Loss: 1.3975, Val Accuracy: 0.5179 Epoch 2454/10000, Train Loss: 1.3764, Train Accuracy: 0.5636, Val Loss: 1.3975, Val Accuracy: 0.5179 Epoch 2455/10000, Train Loss: 1.3846, Train Accuracy: 0.5424, Val Loss: 1.3973, Val Accuracy: 0.5179 Epoch 2456/10000, Train Loss: 1.3758, Train Accuracy: 0.5737, Val Loss: 1.3972, Val Accuracy: 0.5179 Epoch 2457/10000, Train Loss: 1.3727, Train Accuracy: 0.5759, Val Loss: 1.3971, Val Accuracy: 0.5179 Epoch 2458/10000, Train Loss: 1.3730, Train Accuracy: 0.5859, Val Loss: 1.3970, Val Accuracy: 0.5179 Epoch 2459/10000, Train Loss: 1.3780, Train Accuracy: 0.5614, Val Loss: 1.3970, Val Accuracy: 0.5179 Epoch 2460/10000, Train Loss: 1.3727, Train Accuracy: 0.5647, Val Loss: 1.3969, Val Accuracy: 0.5179 Epoch 2461/10000, Train Loss: 1.3796, Train Accuracy: 0.5703, Val Loss: 1.3968, Val Accuracy: 0.5179 Epoch 2462/10000, Train Loss: 1.3766, Train Accuracy: 0.5647, Val Loss: 1.3967, Val Accuracy: 0.5179 Epoch 2463/10000, Train Loss: 1.3752, Train Accuracy: 0.5580, Val Loss: 1.3966, Val Accuracy: 0.5179 Epoch 2464/10000, Train Loss: 1.3740, Train Accuracy: 0.5815, Val Loss: 1.3964, Val Accuracy: 0.5179 Epoch 2465/10000, Train Loss: 1.3759, Train Accuracy: 0.5714, Val Loss: 1.3963, Val Accuracy: 0.5179 Epoch 2466/10000, Train Loss: 1.3837, Train Accuracy: 0.5692, Val Loss: 1.3962, Val Accuracy: 0.5179 Epoch 2467/10000, Train Loss: 1.3716, Train Accuracy: 0.5859, Val Loss: 1.3961, Val Accuracy: 0.5179 Epoch 2468/10000, Train Loss: 1.3767, Train Accuracy: 0.5725, Val Loss: 1.3959, Val Accuracy: 0.5179 Epoch 2469/10000, Train Loss: 1.3694, Train Accuracy: 0.5714, Val Loss: 1.3958, Val Accuracy: 0.5179 Epoch 2470/10000, Train Loss: 1.3760, Train Accuracy: 0.5592, Val Loss: 1.3957, Val Accuracy: 0.5179 Epoch 2471/10000, Train Loss: 1.3815, Train Accuracy: 0.5692, Val Loss: 1.3956, Val Accuracy: 0.5179 Epoch 2472/10000, Train Loss: 1.3695, Train Accuracy: 0.5815, Val Loss: 1.3955, Val Accuracy: 0.5179 Epoch 2473/10000, Train Loss: 1.3750, Train Accuracy: 0.5614, Val Loss: 1.3954, Val Accuracy: 0.5179 Epoch 2474/10000, Train Loss: 1.3784, Train Accuracy: 0.5804, Val Loss: 1.3953, Val Accuracy: 0.5179 Epoch 2475/10000, Train Loss: 1.3779, Train Accuracy: 0.5681, Val Loss: 1.3952, Val Accuracy: 0.5179 Epoch 2476/10000, Train Loss: 1.3773, Train Accuracy: 0.5658, Val Loss: 1.3951, Val Accuracy: 0.5179 Epoch 2477/10000, Train Loss: 1.3734, Train Accuracy: 0.5815, Val Loss: 1.3949, Val Accuracy: 0.5179 Epoch 2478/10000, Train Loss: 1.3777, Train Accuracy: 0.5703, Val Loss: 1.3948, Val Accuracy: 0.5179 Epoch 2479/10000, Train Loss: 1.3731, Train Accuracy: 0.5547, Val Loss: 1.3947, Val Accuracy: 0.5179 Epoch 2480/10000, Train Loss: 1.3755, Train Accuracy: 0.5580, Val Loss: 1.3946, Val Accuracy: 0.5179 Epoch 2481/10000, Train Loss: 1.3719, Train Accuracy: 0.5781, Val Loss: 1.3945, Val Accuracy: 0.5179 Epoch 2482/10000, Train Loss: 1.3793, Train Accuracy: 0.5737, Val Loss: 1.3944, Val Accuracy: 0.5179 Epoch 2483/10000, Train Loss: 1.3732, Train Accuracy: 0.5703, Val Loss: 1.3943, Val Accuracy: 0.5179 Epoch 2484/10000, Train Loss: 1.3775, Train Accuracy: 0.5647, Val Loss: 1.3942, Val Accuracy: 0.5179 Epoch 2485/10000, Train Loss: 1.3737, Train Accuracy: 0.5770, Val Loss: 1.3941, Val Accuracy: 0.5179 Epoch 2486/10000, Train Loss: 1.3773, Train Accuracy: 0.5759, Val Loss: 1.3940, Val Accuracy: 0.5179 Epoch 2487/10000, Train Loss: 1.3763, Train Accuracy: 0.5670, Val Loss: 1.3940, Val Accuracy: 0.5179 Epoch 2488/10000, Train Loss: 1.3715, Train Accuracy: 0.5625, Val Loss: 1.3939, Val Accuracy: 0.5179 Epoch 2489/10000, Train Loss: 1.3730, Train Accuracy: 0.5859, Val Loss: 1.3938, Val Accuracy: 0.5179 Epoch 2490/10000, Train Loss: 1.3818, Train Accuracy: 0.5603, Val Loss: 1.3937, Val Accuracy: 0.5179 Epoch 2491/10000, Train Loss: 1.3769, Train Accuracy: 0.5603, Val Loss: 1.3936, Val Accuracy: 0.5179 Epoch 2492/10000, Train Loss: 1.3688, Train Accuracy: 0.5625, Val Loss: 1.3935, Val Accuracy: 0.5179 Epoch 2493/10000, Train Loss: 1.3772, Train Accuracy: 0.5636, Val Loss: 1.3934, Val Accuracy: 0.5179 Epoch 2494/10000, Train Loss: 1.3685, Train Accuracy: 0.5971, Val Loss: 1.3933, Val Accuracy: 0.5179 Epoch 2495/10000, Train Loss: 1.3705, Train Accuracy: 0.5815, Val Loss: 1.3932, Val Accuracy: 0.5179 Epoch 2496/10000, Train Loss: 1.3783, Train Accuracy: 0.5670, Val Loss: 1.3932, Val Accuracy: 0.5179 Epoch 2497/10000, Train Loss: 1.3744, Train Accuracy: 0.5737, Val Loss: 1.3931, Val Accuracy: 0.5179 Epoch 2498/10000, Train Loss: 1.3703, Train Accuracy: 0.5725, Val Loss: 1.3930, Val Accuracy: 0.5179 Epoch 2499/10000, Train Loss: 1.3661, Train Accuracy: 0.5826, Val Loss: 1.3930, Val Accuracy: 0.5179 Epoch 2500/10000, Train Loss: 1.3739, Train Accuracy: 0.5670, Val Loss: 1.3929, Val Accuracy: 0.5179 Epoch 2501/10000, Train Loss: 1.3735, Train Accuracy: 0.5871, Val Loss: 1.3928, Val Accuracy: 0.5179 Epoch 2502/10000, Train Loss: 1.3697, Train Accuracy: 0.5725, Val Loss: 1.3927, Val Accuracy: 0.5179 Epoch 2503/10000, Train Loss: 1.3692, Train Accuracy: 0.5725, Val Loss: 1.3926, Val Accuracy: 0.5179 Epoch 2504/10000, Train Loss: 1.3727, Train Accuracy: 0.5681, Val Loss: 1.3925, Val Accuracy: 0.5179 Epoch 2505/10000, Train Loss: 1.3706, Train Accuracy: 0.5815, Val Loss: 1.3924, Val Accuracy: 0.5179 Epoch 2506/10000, Train Loss: 1.3718, Train Accuracy: 0.5681, Val Loss: 1.3923, Val Accuracy: 0.5179 Epoch 2507/10000, Train Loss: 1.3706, Train Accuracy: 0.5770, Val Loss: 1.3922, Val Accuracy: 0.5179 Epoch 2508/10000, Train Loss: 1.3694, Train Accuracy: 0.5837, Val Loss: 1.3921, Val Accuracy: 0.5179 Epoch 2509/10000, Train Loss: 1.3670, Train Accuracy: 0.5770, Val Loss: 1.3919, Val Accuracy: 0.5179 Epoch 2510/10000, Train Loss: 1.3749, Train Accuracy: 0.5681, Val Loss: 1.3918, Val Accuracy: 0.5179 Epoch 2511/10000, Train Loss: 1.3690, Train Accuracy: 0.5737, Val Loss: 1.3917, Val Accuracy: 0.5179 Epoch 2512/10000, Train Loss: 1.3682, Train Accuracy: 0.5859, Val Loss: 1.3916, Val Accuracy: 0.5179 Epoch 2513/10000, Train Loss: 1.3754, Train Accuracy: 0.5681, Val Loss: 1.3915, Val Accuracy: 0.5179 Epoch 2514/10000, Train Loss: 1.3682, Train Accuracy: 0.5737, Val Loss: 1.3915, Val Accuracy: 0.5179 Epoch 2515/10000, Train Loss: 1.3698, Train Accuracy: 0.5692, Val Loss: 1.3914, Val Accuracy: 0.5179 Epoch 2516/10000, Train Loss: 1.3743, Train Accuracy: 0.5502, Val Loss: 1.3913, Val Accuracy: 0.5179 Epoch 2517/10000, Train Loss: 1.3714, Train Accuracy: 0.5725, Val Loss: 1.3912, Val Accuracy: 0.5179 Epoch 2518/10000, Train Loss: 1.3655, Train Accuracy: 0.5781, Val Loss: 1.3911, Val Accuracy: 0.5179 Epoch 2519/10000, Train Loss: 1.3647, Train Accuracy: 0.5904, Val Loss: 1.3910, Val Accuracy: 0.5179 Epoch 2520/10000, Train Loss: 1.3668, Train Accuracy: 0.5792, Val Loss: 1.3909, Val Accuracy: 0.5179 Epoch 2521/10000, Train Loss: 1.3729, Train Accuracy: 0.5603, Val Loss: 1.3908, Val Accuracy: 0.5179 Epoch 2522/10000, Train Loss: 1.3748, Train Accuracy: 0.5458, Val Loss: 1.3908, Val Accuracy: 0.5179 Epoch 2523/10000, Train Loss: 1.3737, Train Accuracy: 0.5558, Val Loss: 1.3907, Val Accuracy: 0.5179 Epoch 2524/10000, Train Loss: 1.3725, Train Accuracy: 0.5748, Val Loss: 1.3906, Val Accuracy: 0.5179 Epoch 2525/10000, Train Loss: 1.3727, Train Accuracy: 0.5759, Val Loss: 1.3905, Val Accuracy: 0.5179 Epoch 2526/10000, Train Loss: 1.3766, Train Accuracy: 0.5469, Val Loss: 1.3904, Val Accuracy: 0.5179 Epoch 2527/10000, Train Loss: 1.3684, Train Accuracy: 0.5781, Val Loss: 1.3903, Val Accuracy: 0.5179 Epoch 2528/10000, Train Loss: 1.3652, Train Accuracy: 0.5692, Val Loss: 1.3903, Val Accuracy: 0.5179 Epoch 2529/10000, Train Loss: 1.3699, Train Accuracy: 0.5714, Val Loss: 1.3902, Val Accuracy: 0.5179 Epoch 2530/10000, Train Loss: 1.3701, Train Accuracy: 0.5792, Val Loss: 1.3901, Val Accuracy: 0.5179 Epoch 2531/10000, Train Loss: 1.3770, Train Accuracy: 0.5592, Val Loss: 1.3900, Val Accuracy: 0.5179 Epoch 2532/10000, Train Loss: 1.3632, Train Accuracy: 0.5770, Val Loss: 1.3899, Val Accuracy: 0.5179 Epoch 2533/10000, Train Loss: 1.3695, Train Accuracy: 0.5848, Val Loss: 1.3898, Val Accuracy: 0.5179 Epoch 2534/10000, Train Loss: 1.3748, Train Accuracy: 0.5580, Val Loss: 1.3897, Val Accuracy: 0.5179 Epoch 2535/10000, Train Loss: 1.3637, Train Accuracy: 0.5781, Val Loss: 1.3896, Val Accuracy: 0.5179 Epoch 2536/10000, Train Loss: 1.3645, Train Accuracy: 0.5725, Val Loss: 1.3895, Val Accuracy: 0.5179 Epoch 2537/10000, Train Loss: 1.3628, Train Accuracy: 0.5826, Val Loss: 1.3894, Val Accuracy: 0.5179 Epoch 2538/10000, Train Loss: 1.3586, Train Accuracy: 0.5871, Val Loss: 1.3892, Val Accuracy: 0.5179 Epoch 2539/10000, Train Loss: 1.3634, Train Accuracy: 0.5759, Val Loss: 1.3891, Val Accuracy: 0.5179 Epoch 2540/10000, Train Loss: 1.3698, Train Accuracy: 0.5647, Val Loss: 1.3891, Val Accuracy: 0.5179 Epoch 2541/10000, Train Loss: 1.3690, Train Accuracy: 0.5737, Val Loss: 1.3889, Val Accuracy: 0.5179 Epoch 2542/10000, Train Loss: 1.3603, Train Accuracy: 0.5915, Val Loss: 1.3888, Val Accuracy: 0.5179 Epoch 2543/10000, Train Loss: 1.3616, Train Accuracy: 0.5859, Val Loss: 1.3887, Val Accuracy: 0.5179 Epoch 2544/10000, Train Loss: 1.3671, Train Accuracy: 0.5525, Val Loss: 1.3886, Val Accuracy: 0.5179 Epoch 2545/10000, Train Loss: 1.3639, Train Accuracy: 0.5714, Val Loss: 1.3885, Val Accuracy: 0.5179 Epoch 2546/10000, Train Loss: 1.3703, Train Accuracy: 0.5647, Val Loss: 1.3885, Val Accuracy: 0.5179 Epoch 2547/10000, Train Loss: 1.3680, Train Accuracy: 0.5692, Val Loss: 1.3884, Val Accuracy: 0.5179 Epoch 2548/10000, Train Loss: 1.3664, Train Accuracy: 0.5703, Val Loss: 1.3882, Val Accuracy: 0.5179 Epoch 2549/10000, Train Loss: 1.3699, Train Accuracy: 0.5859, Val Loss: 1.3881, Val Accuracy: 0.5179 Epoch 2550/10000, Train Loss: 1.3634, Train Accuracy: 0.5804, Val Loss: 1.3880, Val Accuracy: 0.5179 Epoch 2551/10000, Train Loss: 1.3573, Train Accuracy: 0.6004, Val Loss: 1.3879, Val Accuracy: 0.5179 Epoch 2552/10000, Train Loss: 1.3681, Train Accuracy: 0.5681, Val Loss: 1.3878, Val Accuracy: 0.5179 Epoch 2553/10000, Train Loss: 1.3615, Train Accuracy: 0.5804, Val Loss: 1.3877, Val Accuracy: 0.5179 Epoch 2554/10000, Train Loss: 1.3609, Train Accuracy: 0.5781, Val Loss: 1.3876, Val Accuracy: 0.5179 Epoch 2555/10000, Train Loss: 1.3589, Train Accuracy: 0.5871, Val Loss: 1.3874, Val Accuracy: 0.5179 Epoch 2556/10000, Train Loss: 1.3642, Train Accuracy: 0.5737, Val Loss: 1.3873, Val Accuracy: 0.5179 Epoch 2557/10000, Train Loss: 1.3626, Train Accuracy: 0.5915, Val Loss: 1.3872, Val Accuracy: 0.5179 Epoch 2558/10000, Train Loss: 1.3569, Train Accuracy: 0.5837, Val Loss: 1.3872, Val Accuracy: 0.5179 Epoch 2559/10000, Train Loss: 1.3670, Train Accuracy: 0.5725, Val Loss: 1.3871, Val Accuracy: 0.5179 Epoch 2560/10000, Train Loss: 1.3644, Train Accuracy: 0.5725, Val Loss: 1.3870, Val Accuracy: 0.5179 Epoch 2561/10000, Train Loss: 1.3669, Train Accuracy: 0.5658, Val Loss: 1.3869, Val Accuracy: 0.5179 Epoch 2562/10000, Train Loss: 1.3706, Train Accuracy: 0.5658, Val Loss: 1.3868, Val Accuracy: 0.5179 Epoch 2563/10000, Train Loss: 1.3584, Train Accuracy: 0.5748, Val Loss: 1.3867, Val Accuracy: 0.5179 Epoch 2564/10000, Train Loss: 1.3643, Train Accuracy: 0.5703, Val Loss: 1.3866, Val Accuracy: 0.5179 Epoch 2565/10000, Train Loss: 1.3573, Train Accuracy: 0.5971, Val Loss: 1.3865, Val Accuracy: 0.5179 Epoch 2566/10000, Train Loss: 1.3596, Train Accuracy: 0.5882, Val Loss: 1.3864, Val Accuracy: 0.5179 Epoch 2567/10000, Train Loss: 1.3695, Train Accuracy: 0.5670, Val Loss: 1.3863, Val Accuracy: 0.5179 Epoch 2568/10000, Train Loss: 1.3635, Train Accuracy: 0.5703, Val Loss: 1.3862, Val Accuracy: 0.5179 Epoch 2569/10000, Train Loss: 1.3706, Train Accuracy: 0.5737, Val Loss: 1.3861, Val Accuracy: 0.5179 Epoch 2570/10000, Train Loss: 1.3656, Train Accuracy: 0.5737, Val Loss: 1.3860, Val Accuracy: 0.5179 Epoch 2571/10000, Train Loss: 1.3664, Train Accuracy: 0.5770, Val Loss: 1.3859, Val Accuracy: 0.5179 Epoch 2572/10000, Train Loss: 1.3566, Train Accuracy: 0.5725, Val Loss: 1.3858, Val Accuracy: 0.5179 Epoch 2573/10000, Train Loss: 1.3574, Train Accuracy: 0.5938, Val Loss: 1.3857, Val Accuracy: 0.5179 Epoch 2574/10000, Train Loss: 1.3691, Train Accuracy: 0.5714, Val Loss: 1.3855, Val Accuracy: 0.5179 Epoch 2575/10000, Train Loss: 1.3552, Train Accuracy: 0.5982, Val Loss: 1.3854, Val Accuracy: 0.5179 Epoch 2576/10000, Train Loss: 1.3640, Train Accuracy: 0.5938, Val Loss: 1.3853, Val Accuracy: 0.5179 Epoch 2577/10000, Train Loss: 1.3527, Train Accuracy: 0.5882, Val Loss: 1.3852, Val Accuracy: 0.5179 Epoch 2578/10000, Train Loss: 1.3667, Train Accuracy: 0.5882, Val Loss: 1.3851, Val Accuracy: 0.5179 Epoch 2579/10000, Train Loss: 1.3649, Train Accuracy: 0.5837, Val Loss: 1.3850, Val Accuracy: 0.5179 Epoch 2580/10000, Train Loss: 1.3553, Train Accuracy: 0.5904, Val Loss: 1.3849, Val Accuracy: 0.5179 Epoch 2581/10000, Train Loss: 1.3616, Train Accuracy: 0.5670, Val Loss: 1.3847, Val Accuracy: 0.5134 Epoch 2582/10000, Train Loss: 1.3624, Train Accuracy: 0.5871, Val Loss: 1.3846, Val Accuracy: 0.5134 Epoch 2583/10000, Train Loss: 1.3613, Train Accuracy: 0.5904, Val Loss: 1.3846, Val Accuracy: 0.5134 Epoch 2584/10000, Train Loss: 1.3602, Train Accuracy: 0.5837, Val Loss: 1.3845, Val Accuracy: 0.5134 Epoch 2585/10000, Train Loss: 1.3630, Train Accuracy: 0.5815, Val Loss: 1.3844, Val Accuracy: 0.5134 Epoch 2586/10000, Train Loss: 1.3682, Train Accuracy: 0.5592, Val Loss: 1.3843, Val Accuracy: 0.5134 Epoch 2587/10000, Train Loss: 1.3601, Train Accuracy: 0.5792, Val Loss: 1.3843, Val Accuracy: 0.5134 Epoch 2588/10000, Train Loss: 1.3631, Train Accuracy: 0.5737, Val Loss: 1.3841, Val Accuracy: 0.5179 Epoch 2589/10000, Train Loss: 1.3635, Train Accuracy: 0.5837, Val Loss: 1.3841, Val Accuracy: 0.5179 Epoch 2590/10000, Train Loss: 1.3580, Train Accuracy: 0.5781, Val Loss: 1.3840, Val Accuracy: 0.5179 Epoch 2591/10000, Train Loss: 1.3626, Train Accuracy: 0.5859, Val Loss: 1.3839, Val Accuracy: 0.5134 Epoch 2592/10000, Train Loss: 1.3597, Train Accuracy: 0.5737, Val Loss: 1.3839, Val Accuracy: 0.5134 Epoch 2593/10000, Train Loss: 1.3523, Train Accuracy: 0.5926, Val Loss: 1.3838, Val Accuracy: 0.5134 Epoch 2594/10000, Train Loss: 1.3542, Train Accuracy: 0.6150, Val Loss: 1.3836, Val Accuracy: 0.5134 Epoch 2595/10000, Train Loss: 1.3561, Train Accuracy: 0.5893, Val Loss: 1.3836, Val Accuracy: 0.5134 Epoch 2596/10000, Train Loss: 1.3690, Train Accuracy: 0.5647, Val Loss: 1.3835, Val Accuracy: 0.5134 Epoch 2597/10000, Train Loss: 1.3548, Train Accuracy: 0.6027, Val Loss: 1.3834, Val Accuracy: 0.5134 Epoch 2598/10000, Train Loss: 1.3643, Train Accuracy: 0.5915, Val Loss: 1.3833, Val Accuracy: 0.5134 Epoch 2599/10000, Train Loss: 1.3630, Train Accuracy: 0.5859, Val Loss: 1.3832, Val Accuracy: 0.5134 Epoch 2600/10000, Train Loss: 1.3581, Train Accuracy: 0.5848, Val Loss: 1.3832, Val Accuracy: 0.5134 Epoch 2601/10000, Train Loss: 1.3524, Train Accuracy: 0.5982, Val Loss: 1.3830, Val Accuracy: 0.5134 Epoch 2602/10000, Train Loss: 1.3503, Train Accuracy: 0.5893, Val Loss: 1.3829, Val Accuracy: 0.5134 Epoch 2603/10000, Train Loss: 1.3536, Train Accuracy: 0.5837, Val Loss: 1.3828, Val Accuracy: 0.5134 Epoch 2604/10000, Train Loss: 1.3596, Train Accuracy: 0.5859, Val Loss: 1.3827, Val Accuracy: 0.5134 Epoch 2605/10000, Train Loss: 1.3504, Train Accuracy: 0.5960, Val Loss: 1.3825, Val Accuracy: 0.5179 Epoch 2606/10000, Train Loss: 1.3562, Train Accuracy: 0.5837, Val Loss: 1.3825, Val Accuracy: 0.5179 Epoch 2607/10000, Train Loss: 1.3613, Train Accuracy: 0.5725, Val Loss: 1.3824, Val Accuracy: 0.5134 Epoch 2608/10000, Train Loss: 1.3595, Train Accuracy: 0.5603, Val Loss: 1.3823, Val Accuracy: 0.5134 Epoch 2609/10000, Train Loss: 1.3534, Train Accuracy: 0.5893, Val Loss: 1.3822, Val Accuracy: 0.5134 Epoch 2610/10000, Train Loss: 1.3645, Train Accuracy: 0.5781, Val Loss: 1.3821, Val Accuracy: 0.5134 Epoch 2611/10000, Train Loss: 1.3584, Train Accuracy: 0.5837, Val Loss: 1.3820, Val Accuracy: 0.5134 Epoch 2612/10000, Train Loss: 1.3619, Train Accuracy: 0.5770, Val Loss: 1.3819, Val Accuracy: 0.5134 Epoch 2613/10000, Train Loss: 1.3619, Train Accuracy: 0.5770, Val Loss: 1.3818, Val Accuracy: 0.5134 Epoch 2614/10000, Train Loss: 1.3613, Train Accuracy: 0.5770, Val Loss: 1.3818, Val Accuracy: 0.5134 Epoch 2615/10000, Train Loss: 1.3616, Train Accuracy: 0.5692, Val Loss: 1.3817, Val Accuracy: 0.5179 Epoch 2616/10000, Train Loss: 1.3562, Train Accuracy: 0.5681, Val Loss: 1.3816, Val Accuracy: 0.5134 Epoch 2617/10000, Train Loss: 1.3558, Train Accuracy: 0.5848, Val Loss: 1.3815, Val Accuracy: 0.5179 Epoch 2618/10000, Train Loss: 1.3540, Train Accuracy: 0.5871, Val Loss: 1.3815, Val Accuracy: 0.5179 Epoch 2619/10000, Train Loss: 1.3574, Train Accuracy: 0.5926, Val Loss: 1.3814, Val Accuracy: 0.5134 Epoch 2620/10000, Train Loss: 1.3571, Train Accuracy: 0.5759, Val Loss: 1.3813, Val Accuracy: 0.5179 Epoch 2621/10000, Train Loss: 1.3562, Train Accuracy: 0.5781, Val Loss: 1.3813, Val Accuracy: 0.5134 Epoch 2622/10000, Train Loss: 1.3525, Train Accuracy: 0.5960, Val Loss: 1.3812, Val Accuracy: 0.5134 Epoch 2623/10000, Train Loss: 1.3595, Train Accuracy: 0.5725, Val Loss: 1.3811, Val Accuracy: 0.5179 Epoch 2624/10000, Train Loss: 1.3562, Train Accuracy: 0.5949, Val Loss: 1.3810, Val Accuracy: 0.5179 Epoch 2625/10000, Train Loss: 1.3620, Train Accuracy: 0.5725, Val Loss: 1.3809, Val Accuracy: 0.5179 Epoch 2626/10000, Train Loss: 1.3595, Train Accuracy: 0.5893, Val Loss: 1.3808, Val Accuracy: 0.5179 Epoch 2627/10000, Train Loss: 1.3513, Train Accuracy: 0.5915, Val Loss: 1.3807, Val Accuracy: 0.5179 Epoch 2628/10000, Train Loss: 1.3530, Train Accuracy: 0.5848, Val Loss: 1.3806, Val Accuracy: 0.5179 Epoch 2629/10000, Train Loss: 1.3650, Train Accuracy: 0.5737, Val Loss: 1.3805, Val Accuracy: 0.5179 Epoch 2630/10000, Train Loss: 1.3494, Train Accuracy: 0.5893, Val Loss: 1.3804, Val Accuracy: 0.5179 Epoch 2631/10000, Train Loss: 1.3626, Train Accuracy: 0.5636, Val Loss: 1.3803, Val Accuracy: 0.5179 Epoch 2632/10000, Train Loss: 1.3436, Train Accuracy: 0.6071, Val Loss: 1.3802, Val Accuracy: 0.5179 Epoch 2633/10000, Train Loss: 1.3576, Train Accuracy: 0.5636, Val Loss: 1.3802, Val Accuracy: 0.5179 Epoch 2634/10000, Train Loss: 1.3588, Train Accuracy: 0.5882, Val Loss: 1.3801, Val Accuracy: 0.5179 Epoch 2635/10000, Train Loss: 1.3534, Train Accuracy: 0.5926, Val Loss: 1.3800, Val Accuracy: 0.5179 Epoch 2636/10000, Train Loss: 1.3578, Train Accuracy: 0.5882, Val Loss: 1.3799, Val Accuracy: 0.5179 Epoch 2637/10000, Train Loss: 1.3545, Train Accuracy: 0.5859, Val Loss: 1.3798, Val Accuracy: 0.5179 Epoch 2638/10000, Train Loss: 1.3537, Train Accuracy: 0.5859, Val Loss: 1.3797, Val Accuracy: 0.5179 Epoch 2639/10000, Train Loss: 1.3549, Train Accuracy: 0.5926, Val Loss: 1.3796, Val Accuracy: 0.5179 Epoch 2640/10000, Train Loss: 1.3537, Train Accuracy: 0.5960, Val Loss: 1.3796, Val Accuracy: 0.5179 Epoch 2641/10000, Train Loss: 1.3538, Train Accuracy: 0.5871, Val Loss: 1.3795, Val Accuracy: 0.5223 Epoch 2642/10000, Train Loss: 1.3611, Train Accuracy: 0.5759, Val Loss: 1.3794, Val Accuracy: 0.5223 Epoch 2643/10000, Train Loss: 1.3529, Train Accuracy: 0.5859, Val Loss: 1.3793, Val Accuracy: 0.5223 Epoch 2644/10000, Train Loss: 1.3529, Train Accuracy: 0.5848, Val Loss: 1.3792, Val Accuracy: 0.5223 Epoch 2645/10000, Train Loss: 1.3504, Train Accuracy: 0.5859, Val Loss: 1.3791, Val Accuracy: 0.5223 Epoch 2646/10000, Train Loss: 1.3515, Train Accuracy: 0.5871, Val Loss: 1.3790, Val Accuracy: 0.5179 Epoch 2647/10000, Train Loss: 1.3544, Train Accuracy: 0.5893, Val Loss: 1.3789, Val Accuracy: 0.5179 Epoch 2648/10000, Train Loss: 1.3592, Train Accuracy: 0.5826, Val Loss: 1.3789, Val Accuracy: 0.5223 Epoch 2649/10000, Train Loss: 1.3576, Train Accuracy: 0.5703, Val Loss: 1.3788, Val Accuracy: 0.5223 Epoch 2650/10000, Train Loss: 1.3569, Train Accuracy: 0.5714, Val Loss: 1.3787, Val Accuracy: 0.5223 Epoch 2651/10000, Train Loss: 1.3524, Train Accuracy: 0.5826, Val Loss: 1.3786, Val Accuracy: 0.5223 Epoch 2652/10000, Train Loss: 1.3569, Train Accuracy: 0.5804, Val Loss: 1.3785, Val Accuracy: 0.5223 Epoch 2653/10000, Train Loss: 1.3457, Train Accuracy: 0.5815, Val Loss: 1.3783, Val Accuracy: 0.5223 Epoch 2654/10000, Train Loss: 1.3492, Train Accuracy: 0.6004, Val Loss: 1.3783, Val Accuracy: 0.5223 Epoch 2655/10000, Train Loss: 1.3545, Train Accuracy: 0.5871, Val Loss: 1.3782, Val Accuracy: 0.5223 Epoch 2656/10000, Train Loss: 1.3456, Train Accuracy: 0.5915, Val Loss: 1.3781, Val Accuracy: 0.5223 Epoch 2657/10000, Train Loss: 1.3447, Train Accuracy: 0.5982, Val Loss: 1.3780, Val Accuracy: 0.5223 Epoch 2658/10000, Train Loss: 1.3508, Train Accuracy: 0.5804, Val Loss: 1.3780, Val Accuracy: 0.5223 Epoch 2659/10000, Train Loss: 1.3578, Train Accuracy: 0.5748, Val Loss: 1.3778, Val Accuracy: 0.5223 Epoch 2660/10000, Train Loss: 1.3571, Train Accuracy: 0.5893, Val Loss: 1.3777, Val Accuracy: 0.5223 Epoch 2661/10000, Train Loss: 1.3477, Train Accuracy: 0.5882, Val Loss: 1.3776, Val Accuracy: 0.5223 Epoch 2662/10000, Train Loss: 1.3483, Train Accuracy: 0.6038, Val Loss: 1.3775, Val Accuracy: 0.5223 Epoch 2663/10000, Train Loss: 1.3497, Train Accuracy: 0.5938, Val Loss: 1.3775, Val Accuracy: 0.5223 Epoch 2664/10000, Train Loss: 1.3519, Train Accuracy: 0.6060, Val Loss: 1.3774, Val Accuracy: 0.5223 Epoch 2665/10000, Train Loss: 1.3523, Train Accuracy: 0.5938, Val Loss: 1.3773, Val Accuracy: 0.5268 Epoch 2666/10000, Train Loss: 1.3537, Train Accuracy: 0.5837, Val Loss: 1.3772, Val Accuracy: 0.5268 Epoch 2667/10000, Train Loss: 1.3496, Train Accuracy: 0.5848, Val Loss: 1.3771, Val Accuracy: 0.5268 Epoch 2668/10000, Train Loss: 1.3444, Train Accuracy: 0.5949, Val Loss: 1.3770, Val Accuracy: 0.5268 Epoch 2669/10000, Train Loss: 1.3559, Train Accuracy: 0.5871, Val Loss: 1.3769, Val Accuracy: 0.5268 Epoch 2670/10000, Train Loss: 1.3528, Train Accuracy: 0.5882, Val Loss: 1.3768, Val Accuracy: 0.5268 Epoch 2671/10000, Train Loss: 1.3564, Train Accuracy: 0.5792, Val Loss: 1.3767, Val Accuracy: 0.5268 Epoch 2672/10000, Train Loss: 1.3484, Train Accuracy: 0.6083, Val Loss: 1.3766, Val Accuracy: 0.5268 Epoch 2673/10000, Train Loss: 1.3485, Train Accuracy: 0.5904, Val Loss: 1.3765, Val Accuracy: 0.5268 Epoch 2674/10000, Train Loss: 1.3446, Train Accuracy: 0.6071, Val Loss: 1.3764, Val Accuracy: 0.5268 Epoch 2675/10000, Train Loss: 1.3425, Train Accuracy: 0.6116, Val Loss: 1.3763, Val Accuracy: 0.5268 Epoch 2676/10000, Train Loss: 1.3519, Train Accuracy: 0.5837, Val Loss: 1.3762, Val Accuracy: 0.5268 Epoch 2677/10000, Train Loss: 1.3477, Train Accuracy: 0.6049, Val Loss: 1.3760, Val Accuracy: 0.5268 Epoch 2678/10000, Train Loss: 1.3497, Train Accuracy: 0.5647, Val Loss: 1.3760, Val Accuracy: 0.5268 Epoch 2679/10000, Train Loss: 1.3461, Train Accuracy: 0.5960, Val Loss: 1.3759, Val Accuracy: 0.5268 Epoch 2680/10000, Train Loss: 1.3531, Train Accuracy: 0.5982, Val Loss: 1.3758, Val Accuracy: 0.5268 Epoch 2681/10000, Train Loss: 1.3489, Train Accuracy: 0.5904, Val Loss: 1.3757, Val Accuracy: 0.5268 Epoch 2682/10000, Train Loss: 1.3408, Train Accuracy: 0.6038, Val Loss: 1.3757, Val Accuracy: 0.5312 Epoch 2683/10000, Train Loss: 1.3452, Train Accuracy: 0.5915, Val Loss: 1.3756, Val Accuracy: 0.5312 Epoch 2684/10000, Train Loss: 1.3526, Train Accuracy: 0.5759, Val Loss: 1.3756, Val Accuracy: 0.5312 Epoch 2685/10000, Train Loss: 1.3465, Train Accuracy: 0.5971, Val Loss: 1.3754, Val Accuracy: 0.5312 Epoch 2686/10000, Train Loss: 1.3467, Train Accuracy: 0.6049, Val Loss: 1.3753, Val Accuracy: 0.5312 Epoch 2687/10000, Train Loss: 1.3543, Train Accuracy: 0.5681, Val Loss: 1.3752, Val Accuracy: 0.5312 Epoch 2688/10000, Train Loss: 1.3454, Train Accuracy: 0.5949, Val Loss: 1.3750, Val Accuracy: 0.5312 Epoch 2689/10000, Train Loss: 1.3463, Train Accuracy: 0.5982, Val Loss: 1.3749, Val Accuracy: 0.5312 Epoch 2690/10000, Train Loss: 1.3451, Train Accuracy: 0.5904, Val Loss: 1.3748, Val Accuracy: 0.5312 Epoch 2691/10000, Train Loss: 1.3470, Train Accuracy: 0.5949, Val Loss: 1.3747, Val Accuracy: 0.5312 Epoch 2692/10000, Train Loss: 1.3478, Train Accuracy: 0.5915, Val Loss: 1.3747, Val Accuracy: 0.5312 Epoch 2693/10000, Train Loss: 1.3552, Train Accuracy: 0.5737, Val Loss: 1.3746, Val Accuracy: 0.5312 Epoch 2694/10000, Train Loss: 1.3440, Train Accuracy: 0.5993, Val Loss: 1.3745, Val Accuracy: 0.5312 Epoch 2695/10000, Train Loss: 1.3464, Train Accuracy: 0.5893, Val Loss: 1.3744, Val Accuracy: 0.5312 Epoch 2696/10000, Train Loss: 1.3474, Train Accuracy: 0.5971, Val Loss: 1.3743, Val Accuracy: 0.5312 Epoch 2697/10000, Train Loss: 1.3541, Train Accuracy: 0.5859, Val Loss: 1.3743, Val Accuracy: 0.5312 Epoch 2698/10000, Train Loss: 1.3445, Train Accuracy: 0.5938, Val Loss: 1.3742, Val Accuracy: 0.5312 Epoch 2699/10000, Train Loss: 1.3469, Train Accuracy: 0.5893, Val Loss: 1.3741, Val Accuracy: 0.5312 Epoch 2700/10000, Train Loss: 1.3365, Train Accuracy: 0.6094, Val Loss: 1.3740, Val Accuracy: 0.5312 Epoch 2701/10000, Train Loss: 1.3439, Train Accuracy: 0.5926, Val Loss: 1.3739, Val Accuracy: 0.5312 Epoch 2702/10000, Train Loss: 1.3539, Train Accuracy: 0.5792, Val Loss: 1.3738, Val Accuracy: 0.5312 Epoch 2703/10000, Train Loss: 1.3476, Train Accuracy: 0.5804, Val Loss: 1.3737, Val Accuracy: 0.5312 Epoch 2704/10000, Train Loss: 1.3505, Train Accuracy: 0.5859, Val Loss: 1.3736, Val Accuracy: 0.5312 Epoch 2705/10000, Train Loss: 1.3487, Train Accuracy: 0.5915, Val Loss: 1.3735, Val Accuracy: 0.5312 Epoch 2706/10000, Train Loss: 1.3469, Train Accuracy: 0.5960, Val Loss: 1.3734, Val Accuracy: 0.5312 Epoch 2707/10000, Train Loss: 1.3474, Train Accuracy: 0.5882, Val Loss: 1.3733, Val Accuracy: 0.5312 Epoch 2708/10000, Train Loss: 1.3486, Train Accuracy: 0.5915, Val Loss: 1.3732, Val Accuracy: 0.5312 Epoch 2709/10000, Train Loss: 1.3427, Train Accuracy: 0.6004, Val Loss: 1.3732, Val Accuracy: 0.5312 Epoch 2710/10000, Train Loss: 1.3388, Train Accuracy: 0.6094, Val Loss: 1.3731, Val Accuracy: 0.5312 Epoch 2711/10000, Train Loss: 1.3429, Train Accuracy: 0.5915, Val Loss: 1.3730, Val Accuracy: 0.5312 Epoch 2712/10000, Train Loss: 1.3586, Train Accuracy: 0.5837, Val Loss: 1.3729, Val Accuracy: 0.5312 Epoch 2713/10000, Train Loss: 1.3479, Train Accuracy: 0.5926, Val Loss: 1.3728, Val Accuracy: 0.5312 Epoch 2714/10000, Train Loss: 1.3365, Train Accuracy: 0.6116, Val Loss: 1.3727, Val Accuracy: 0.5312 Epoch 2715/10000, Train Loss: 1.3536, Train Accuracy: 0.5804, Val Loss: 1.3726, Val Accuracy: 0.5312 Epoch 2716/10000, Train Loss: 1.3428, Train Accuracy: 0.6071, Val Loss: 1.3725, Val Accuracy: 0.5312 Epoch 2717/10000, Train Loss: 1.3379, Train Accuracy: 0.6071, Val Loss: 1.3724, Val Accuracy: 0.5312 Epoch 2718/10000, Train Loss: 1.3446, Train Accuracy: 0.5915, Val Loss: 1.3723, Val Accuracy: 0.5268 Epoch 2719/10000, Train Loss: 1.3515, Train Accuracy: 0.5804, Val Loss: 1.3722, Val Accuracy: 0.5268 Epoch 2720/10000, Train Loss: 1.3452, Train Accuracy: 0.5949, Val Loss: 1.3722, Val Accuracy: 0.5223 Epoch 2721/10000, Train Loss: 1.3357, Train Accuracy: 0.6194, Val Loss: 1.3721, Val Accuracy: 0.5223 Epoch 2722/10000, Train Loss: 1.3433, Train Accuracy: 0.5938, Val Loss: 1.3720, Val Accuracy: 0.5223 Epoch 2723/10000, Train Loss: 1.3516, Train Accuracy: 0.5926, Val Loss: 1.3719, Val Accuracy: 0.5268 Epoch 2724/10000, Train Loss: 1.3496, Train Accuracy: 0.5915, Val Loss: 1.3718, Val Accuracy: 0.5223 Epoch 2725/10000, Train Loss: 1.3452, Train Accuracy: 0.5871, Val Loss: 1.3717, Val Accuracy: 0.5268 Epoch 2726/10000, Train Loss: 1.3445, Train Accuracy: 0.6038, Val Loss: 1.3716, Val Accuracy: 0.5223 Epoch 2727/10000, Train Loss: 1.3364, Train Accuracy: 0.6194, Val Loss: 1.3715, Val Accuracy: 0.5312 Epoch 2728/10000, Train Loss: 1.3348, Train Accuracy: 0.6116, Val Loss: 1.3714, Val Accuracy: 0.5223 Epoch 2729/10000, Train Loss: 1.3410, Train Accuracy: 0.6027, Val Loss: 1.3713, Val Accuracy: 0.5179 Epoch 2730/10000, Train Loss: 1.3355, Train Accuracy: 0.6038, Val Loss: 1.3713, Val Accuracy: 0.5179 Epoch 2731/10000, Train Loss: 1.3395, Train Accuracy: 0.6116, Val Loss: 1.3712, Val Accuracy: 0.5223 Epoch 2732/10000, Train Loss: 1.3495, Train Accuracy: 0.5759, Val Loss: 1.3712, Val Accuracy: 0.5223 Epoch 2733/10000, Train Loss: 1.3377, Train Accuracy: 0.6060, Val Loss: 1.3711, Val Accuracy: 0.5223 Epoch 2734/10000, Train Loss: 1.3369, Train Accuracy: 0.5938, Val Loss: 1.3710, Val Accuracy: 0.5223 Epoch 2735/10000, Train Loss: 1.3406, Train Accuracy: 0.6060, Val Loss: 1.3709, Val Accuracy: 0.5268 Epoch 2736/10000, Train Loss: 1.3448, Train Accuracy: 0.5837, Val Loss: 1.3708, Val Accuracy: 0.5268 Epoch 2737/10000, Train Loss: 1.3415, Train Accuracy: 0.5893, Val Loss: 1.3707, Val Accuracy: 0.5268 Epoch 2738/10000, Train Loss: 1.3414, Train Accuracy: 0.5993, Val Loss: 1.3706, Val Accuracy: 0.5268 Epoch 2739/10000, Train Loss: 1.3384, Train Accuracy: 0.6094, Val Loss: 1.3706, Val Accuracy: 0.5268 Epoch 2740/10000, Train Loss: 1.3430, Train Accuracy: 0.5815, Val Loss: 1.3705, Val Accuracy: 0.5268 Epoch 2741/10000, Train Loss: 1.3509, Train Accuracy: 0.5848, Val Loss: 1.3704, Val Accuracy: 0.5268 Epoch 2742/10000, Train Loss: 1.3459, Train Accuracy: 0.5893, Val Loss: 1.3703, Val Accuracy: 0.5268 Epoch 2743/10000, Train Loss: 1.3341, Train Accuracy: 0.6094, Val Loss: 1.3702, Val Accuracy: 0.5268 Epoch 2744/10000, Train Loss: 1.3419, Train Accuracy: 0.6027, Val Loss: 1.3701, Val Accuracy: 0.5268 Epoch 2745/10000, Train Loss: 1.3436, Train Accuracy: 0.5915, Val Loss: 1.3700, Val Accuracy: 0.5268 Epoch 2746/10000, Train Loss: 1.3418, Train Accuracy: 0.5938, Val Loss: 1.3699, Val Accuracy: 0.5268 Epoch 2747/10000, Train Loss: 1.3436, Train Accuracy: 0.5859, Val Loss: 1.3699, Val Accuracy: 0.5268 Epoch 2748/10000, Train Loss: 1.3446, Train Accuracy: 0.5960, Val Loss: 1.3698, Val Accuracy: 0.5268 Epoch 2749/10000, Train Loss: 1.3476, Train Accuracy: 0.5848, Val Loss: 1.3696, Val Accuracy: 0.5268 Epoch 2750/10000, Train Loss: 1.3453, Train Accuracy: 0.5949, Val Loss: 1.3695, Val Accuracy: 0.5268 Epoch 2751/10000, Train Loss: 1.3396, Train Accuracy: 0.6004, Val Loss: 1.3695, Val Accuracy: 0.5268 Epoch 2752/10000, Train Loss: 1.3347, Train Accuracy: 0.6150, Val Loss: 1.3694, Val Accuracy: 0.5268 Epoch 2753/10000, Train Loss: 1.3431, Train Accuracy: 0.5993, Val Loss: 1.3694, Val Accuracy: 0.5268 Epoch 2754/10000, Train Loss: 1.3389, Train Accuracy: 0.5971, Val Loss: 1.3693, Val Accuracy: 0.5268 Epoch 2755/10000, Train Loss: 1.3422, Train Accuracy: 0.5893, Val Loss: 1.3692, Val Accuracy: 0.5268 Epoch 2756/10000, Train Loss: 1.3380, Train Accuracy: 0.5960, Val Loss: 1.3691, Val Accuracy: 0.5268 Epoch 2757/10000, Train Loss: 1.3389, Train Accuracy: 0.6060, Val Loss: 1.3690, Val Accuracy: 0.5268 Epoch 2758/10000, Train Loss: 1.3318, Train Accuracy: 0.6161, Val Loss: 1.3689, Val Accuracy: 0.5268 Epoch 2759/10000, Train Loss: 1.3425, Train Accuracy: 0.6060, Val Loss: 1.3688, Val Accuracy: 0.5268 Epoch 2760/10000, Train Loss: 1.3369, Train Accuracy: 0.6016, Val Loss: 1.3687, Val Accuracy: 0.5268 Epoch 2761/10000, Train Loss: 1.3412, Train Accuracy: 0.6016, Val Loss: 1.3686, Val Accuracy: 0.5268 Epoch 2762/10000, Train Loss: 1.3424, Train Accuracy: 0.6004, Val Loss: 1.3685, Val Accuracy: 0.5268 Epoch 2763/10000, Train Loss: 1.3449, Train Accuracy: 0.5837, Val Loss: 1.3684, Val Accuracy: 0.5268 Epoch 2764/10000, Train Loss: 1.3357, Train Accuracy: 0.6116, Val Loss: 1.3683, Val Accuracy: 0.5268 Epoch 2765/10000, Train Loss: 1.3302, Train Accuracy: 0.6105, Val Loss: 1.3682, Val Accuracy: 0.5268 Epoch 2766/10000, Train Loss: 1.3402, Train Accuracy: 0.5949, Val Loss: 1.3681, Val Accuracy: 0.5268 Epoch 2767/10000, Train Loss: 1.3362, Train Accuracy: 0.5926, Val Loss: 1.3680, Val Accuracy: 0.5268 Epoch 2768/10000, Train Loss: 1.3450, Train Accuracy: 0.5871, Val Loss: 1.3679, Val Accuracy: 0.5268 Epoch 2769/10000, Train Loss: 1.3455, Train Accuracy: 0.5748, Val Loss: 1.3678, Val Accuracy: 0.5268 Epoch 2770/10000, Train Loss: 1.3420, Train Accuracy: 0.5915, Val Loss: 1.3677, Val Accuracy: 0.5268 Epoch 2771/10000, Train Loss: 1.3351, Train Accuracy: 0.6083, Val Loss: 1.3677, Val Accuracy: 0.5268 Epoch 2772/10000, Train Loss: 1.3408, Train Accuracy: 0.6038, Val Loss: 1.3676, Val Accuracy: 0.5268 Epoch 2773/10000, Train Loss: 1.3335, Train Accuracy: 0.6127, Val Loss: 1.3675, Val Accuracy: 0.5268 Epoch 2774/10000, Train Loss: 1.3378, Train Accuracy: 0.5960, Val Loss: 1.3674, Val Accuracy: 0.5268 Epoch 2775/10000, Train Loss: 1.3371, Train Accuracy: 0.6127, Val Loss: 1.3673, Val Accuracy: 0.5268 Epoch 2776/10000, Train Loss: 1.3431, Train Accuracy: 0.6016, Val Loss: 1.3673, Val Accuracy: 0.5268 Epoch 2777/10000, Train Loss: 1.3415, Train Accuracy: 0.5971, Val Loss: 1.3672, Val Accuracy: 0.5268 Epoch 2778/10000, Train Loss: 1.3359, Train Accuracy: 0.6060, Val Loss: 1.3671, Val Accuracy: 0.5268 Epoch 2779/10000, Train Loss: 1.3488, Train Accuracy: 0.5770, Val Loss: 1.3670, Val Accuracy: 0.5268 Epoch 2780/10000, Train Loss: 1.3273, Train Accuracy: 0.6071, Val Loss: 1.3669, Val Accuracy: 0.5268 Epoch 2781/10000, Train Loss: 1.3322, Train Accuracy: 0.6116, Val Loss: 1.3668, Val Accuracy: 0.5268 Epoch 2782/10000, Train Loss: 1.3351, Train Accuracy: 0.5993, Val Loss: 1.3668, Val Accuracy: 0.5268 Epoch 2783/10000, Train Loss: 1.3357, Train Accuracy: 0.6105, Val Loss: 1.3667, Val Accuracy: 0.5268 Epoch 2784/10000, Train Loss: 1.3335, Train Accuracy: 0.6060, Val Loss: 1.3666, Val Accuracy: 0.5312 Epoch 2785/10000, Train Loss: 1.3449, Train Accuracy: 0.5893, Val Loss: 1.3665, Val Accuracy: 0.5268 Epoch 2786/10000, Train Loss: 1.3360, Train Accuracy: 0.6161, Val Loss: 1.3664, Val Accuracy: 0.5268 Epoch 2787/10000, Train Loss: 1.3359, Train Accuracy: 0.6049, Val Loss: 1.3664, Val Accuracy: 0.5268 Epoch 2788/10000, Train Loss: 1.3440, Train Accuracy: 0.5804, Val Loss: 1.3663, Val Accuracy: 0.5268 Epoch 2789/10000, Train Loss: 1.3456, Train Accuracy: 0.5971, Val Loss: 1.3663, Val Accuracy: 0.5312 Epoch 2790/10000, Train Loss: 1.3397, Train Accuracy: 0.5915, Val Loss: 1.3662, Val Accuracy: 0.5312 Epoch 2791/10000, Train Loss: 1.3316, Train Accuracy: 0.6150, Val Loss: 1.3661, Val Accuracy: 0.5312 Epoch 2792/10000, Train Loss: 1.3353, Train Accuracy: 0.5949, Val Loss: 1.3660, Val Accuracy: 0.5312 Epoch 2793/10000, Train Loss: 1.3334, Train Accuracy: 0.5971, Val Loss: 1.3659, Val Accuracy: 0.5312 Epoch 2794/10000, Train Loss: 1.3249, Train Accuracy: 0.6194, Val Loss: 1.3658, Val Accuracy: 0.5312 Epoch 2795/10000, Train Loss: 1.3346, Train Accuracy: 0.5982, Val Loss: 1.3657, Val Accuracy: 0.5312 Epoch 2796/10000, Train Loss: 1.3344, Train Accuracy: 0.6049, Val Loss: 1.3657, Val Accuracy: 0.5312 Epoch 2797/10000, Train Loss: 1.3421, Train Accuracy: 0.5949, Val Loss: 1.3656, Val Accuracy: 0.5312 Epoch 2798/10000, Train Loss: 1.3347, Train Accuracy: 0.6071, Val Loss: 1.3655, Val Accuracy: 0.5312 Epoch 2799/10000, Train Loss: 1.3320, Train Accuracy: 0.6116, Val Loss: 1.3655, Val Accuracy: 0.5312 Epoch 2800/10000, Train Loss: 1.3380, Train Accuracy: 0.5993, Val Loss: 1.3654, Val Accuracy: 0.5312 Epoch 2801/10000, Train Loss: 1.3271, Train Accuracy: 0.6250, Val Loss: 1.3653, Val Accuracy: 0.5312 Epoch 2802/10000, Train Loss: 1.3401, Train Accuracy: 0.5926, Val Loss: 1.3652, Val Accuracy: 0.5312 Epoch 2803/10000, Train Loss: 1.3370, Train Accuracy: 0.6016, Val Loss: 1.3651, Val Accuracy: 0.5312 Epoch 2804/10000, Train Loss: 1.3326, Train Accuracy: 0.6138, Val Loss: 1.3651, Val Accuracy: 0.5312 Epoch 2805/10000, Train Loss: 1.3387, Train Accuracy: 0.5926, Val Loss: 1.3650, Val Accuracy: 0.5312 Epoch 2806/10000, Train Loss: 1.3292, Train Accuracy: 0.5871, Val Loss: 1.3649, Val Accuracy: 0.5312 Epoch 2807/10000, Train Loss: 1.3400, Train Accuracy: 0.5781, Val Loss: 1.3649, Val Accuracy: 0.5312 Epoch 2808/10000, Train Loss: 1.3359, Train Accuracy: 0.6038, Val Loss: 1.3648, Val Accuracy: 0.5312 Epoch 2809/10000, Train Loss: 1.3323, Train Accuracy: 0.6094, Val Loss: 1.3647, Val Accuracy: 0.5312 Epoch 2810/10000, Train Loss: 1.3389, Train Accuracy: 0.6116, Val Loss: 1.3646, Val Accuracy: 0.5312 Epoch 2811/10000, Train Loss: 1.3265, Train Accuracy: 0.6127, Val Loss: 1.3645, Val Accuracy: 0.5312 Epoch 2812/10000, Train Loss: 1.3338, Train Accuracy: 0.6083, Val Loss: 1.3644, Val Accuracy: 0.5312 Epoch 2813/10000, Train Loss: 1.3356, Train Accuracy: 0.6161, Val Loss: 1.3644, Val Accuracy: 0.5312 Epoch 2814/10000, Train Loss: 1.3329, Train Accuracy: 0.5960, Val Loss: 1.3643, Val Accuracy: 0.5312 Epoch 2815/10000, Train Loss: 1.3429, Train Accuracy: 0.5837, Val Loss: 1.3643, Val Accuracy: 0.5312 Epoch 2816/10000, Train Loss: 1.3291, Train Accuracy: 0.6183, Val Loss: 1.3642, Val Accuracy: 0.5312 Epoch 2817/10000, Train Loss: 1.3300, Train Accuracy: 0.6138, Val Loss: 1.3640, Val Accuracy: 0.5312 Epoch 2818/10000, Train Loss: 1.3373, Train Accuracy: 0.5904, Val Loss: 1.3639, Val Accuracy: 0.5312 Epoch 2819/10000, Train Loss: 1.3410, Train Accuracy: 0.6004, Val Loss: 1.3639, Val Accuracy: 0.5312 Epoch 2820/10000, Train Loss: 1.3378, Train Accuracy: 0.5926, Val Loss: 1.3637, Val Accuracy: 0.5312 Epoch 2821/10000, Train Loss: 1.3354, Train Accuracy: 0.5982, Val Loss: 1.3636, Val Accuracy: 0.5312 Epoch 2822/10000, Train Loss: 1.3311, Train Accuracy: 0.6094, Val Loss: 1.3635, Val Accuracy: 0.5312 Epoch 2823/10000, Train Loss: 1.3257, Train Accuracy: 0.6049, Val Loss: 1.3634, Val Accuracy: 0.5312 Epoch 2824/10000, Train Loss: 1.3313, Train Accuracy: 0.6071, Val Loss: 1.3633, Val Accuracy: 0.5312 Epoch 2825/10000, Train Loss: 1.3359, Train Accuracy: 0.5971, Val Loss: 1.3633, Val Accuracy: 0.5357 Epoch 2826/10000, Train Loss: 1.3453, Train Accuracy: 0.5915, Val Loss: 1.3632, Val Accuracy: 0.5312 Epoch 2827/10000, Train Loss: 1.3388, Train Accuracy: 0.5993, Val Loss: 1.3632, Val Accuracy: 0.5357 Epoch 2828/10000, Train Loss: 1.3324, Train Accuracy: 0.6116, Val Loss: 1.3631, Val Accuracy: 0.5357 Epoch 2829/10000, Train Loss: 1.3353, Train Accuracy: 0.6138, Val Loss: 1.3630, Val Accuracy: 0.5357 Epoch 2830/10000, Train Loss: 1.3259, Train Accuracy: 0.6228, Val Loss: 1.3629, Val Accuracy: 0.5357 Epoch 2831/10000, Train Loss: 1.3370, Train Accuracy: 0.6071, Val Loss: 1.3628, Val Accuracy: 0.5357 Epoch 2832/10000, Train Loss: 1.3359, Train Accuracy: 0.5804, Val Loss: 1.3627, Val Accuracy: 0.5357 Epoch 2833/10000, Train Loss: 1.3275, Train Accuracy: 0.6116, Val Loss: 1.3626, Val Accuracy: 0.5357 Epoch 2834/10000, Train Loss: 1.3307, Train Accuracy: 0.5993, Val Loss: 1.3626, Val Accuracy: 0.5357 Epoch 2835/10000, Train Loss: 1.3354, Train Accuracy: 0.6038, Val Loss: 1.3625, Val Accuracy: 0.5357 Epoch 2836/10000, Train Loss: 1.3290, Train Accuracy: 0.6027, Val Loss: 1.3624, Val Accuracy: 0.5357 Epoch 2837/10000, Train Loss: 1.3313, Train Accuracy: 0.5982, Val Loss: 1.3624, Val Accuracy: 0.5357 Epoch 2838/10000, Train Loss: 1.3347, Train Accuracy: 0.5893, Val Loss: 1.3623, Val Accuracy: 0.5402 Epoch 2839/10000, Train Loss: 1.3334, Train Accuracy: 0.6049, Val Loss: 1.3622, Val Accuracy: 0.5402 Epoch 2840/10000, Train Loss: 1.3314, Train Accuracy: 0.5949, Val Loss: 1.3622, Val Accuracy: 0.5402 Epoch 2841/10000, Train Loss: 1.3329, Train Accuracy: 0.5982, Val Loss: 1.3620, Val Accuracy: 0.5402 Epoch 2842/10000, Train Loss: 1.3326, Train Accuracy: 0.6116, Val Loss: 1.3620, Val Accuracy: 0.5402 Epoch 2843/10000, Train Loss: 1.3308, Train Accuracy: 0.5993, Val Loss: 1.3619, Val Accuracy: 0.5402 Epoch 2844/10000, Train Loss: 1.3452, Train Accuracy: 0.5826, Val Loss: 1.3618, Val Accuracy: 0.5402 Epoch 2845/10000, Train Loss: 1.3308, Train Accuracy: 0.6105, Val Loss: 1.3617, Val Accuracy: 0.5402 Epoch 2846/10000, Train Loss: 1.3276, Train Accuracy: 0.6060, Val Loss: 1.3616, Val Accuracy: 0.5402 Epoch 2847/10000, Train Loss: 1.3298, Train Accuracy: 0.6116, Val Loss: 1.3616, Val Accuracy: 0.5402 Epoch 2848/10000, Train Loss: 1.3242, Train Accuracy: 0.6071, Val Loss: 1.3615, Val Accuracy: 0.5402 Epoch 2849/10000, Train Loss: 1.3231, Train Accuracy: 0.6060, Val Loss: 1.3614, Val Accuracy: 0.5402 Epoch 2850/10000, Train Loss: 1.3345, Train Accuracy: 0.6027, Val Loss: 1.3613, Val Accuracy: 0.5402 Epoch 2851/10000, Train Loss: 1.3352, Train Accuracy: 0.5971, Val Loss: 1.3612, Val Accuracy: 0.5402 Epoch 2852/10000, Train Loss: 1.3323, Train Accuracy: 0.5938, Val Loss: 1.3611, Val Accuracy: 0.5402 Epoch 2853/10000, Train Loss: 1.3304, Train Accuracy: 0.6016, Val Loss: 1.3610, Val Accuracy: 0.5402 Epoch 2854/10000, Train Loss: 1.3243, Train Accuracy: 0.5971, Val Loss: 1.3609, Val Accuracy: 0.5402 Epoch 2855/10000, Train Loss: 1.3228, Train Accuracy: 0.6194, Val Loss: 1.3608, Val Accuracy: 0.5402 Epoch 2856/10000, Train Loss: 1.3394, Train Accuracy: 0.5859, Val Loss: 1.3608, Val Accuracy: 0.5402 Epoch 2857/10000, Train Loss: 1.3300, Train Accuracy: 0.6094, Val Loss: 1.3607, Val Accuracy: 0.5402 Epoch 2858/10000, Train Loss: 1.3349, Train Accuracy: 0.6038, Val Loss: 1.3606, Val Accuracy: 0.5402 Epoch 2859/10000, Train Loss: 1.3377, Train Accuracy: 0.5848, Val Loss: 1.3606, Val Accuracy: 0.5402 Epoch 2860/10000, Train Loss: 1.3239, Train Accuracy: 0.6105, Val Loss: 1.3605, Val Accuracy: 0.5402 Epoch 2861/10000, Train Loss: 1.3218, Train Accuracy: 0.6217, Val Loss: 1.3604, Val Accuracy: 0.5402 Epoch 2862/10000, Train Loss: 1.3319, Train Accuracy: 0.6205, Val Loss: 1.3603, Val Accuracy: 0.5402 Epoch 2863/10000, Train Loss: 1.3305, Train Accuracy: 0.5949, Val Loss: 1.3601, Val Accuracy: 0.5402 Epoch 2864/10000, Train Loss: 1.3285, Train Accuracy: 0.6049, Val Loss: 1.3600, Val Accuracy: 0.5402 Epoch 2865/10000, Train Loss: 1.3299, Train Accuracy: 0.6083, Val Loss: 1.3599, Val Accuracy: 0.5402 Epoch 2866/10000, Train Loss: 1.3371, Train Accuracy: 0.5993, Val Loss: 1.3598, Val Accuracy: 0.5402 Epoch 2867/10000, Train Loss: 1.3220, Train Accuracy: 0.6138, Val Loss: 1.3598, Val Accuracy: 0.5402 Epoch 2868/10000, Train Loss: 1.3261, Train Accuracy: 0.6150, Val Loss: 1.3597, Val Accuracy: 0.5402 Epoch 2869/10000, Train Loss: 1.3325, Train Accuracy: 0.5993, Val Loss: 1.3597, Val Accuracy: 0.5402 Epoch 2870/10000, Train Loss: 1.3323, Train Accuracy: 0.6105, Val Loss: 1.3595, Val Accuracy: 0.5402 Epoch 2871/10000, Train Loss: 1.3273, Train Accuracy: 0.6071, Val Loss: 1.3594, Val Accuracy: 0.5402 Epoch 2872/10000, Train Loss: 1.3175, Train Accuracy: 0.6228, Val Loss: 1.3593, Val Accuracy: 0.5402 Epoch 2873/10000, Train Loss: 1.3265, Train Accuracy: 0.6116, Val Loss: 1.3592, Val Accuracy: 0.5402 Epoch 2874/10000, Train Loss: 1.3278, Train Accuracy: 0.5993, Val Loss: 1.3591, Val Accuracy: 0.5402 Epoch 2875/10000, Train Loss: 1.3332, Train Accuracy: 0.6027, Val Loss: 1.3590, Val Accuracy: 0.5402 Epoch 2876/10000, Train Loss: 1.3270, Train Accuracy: 0.6027, Val Loss: 1.3589, Val Accuracy: 0.5402 Epoch 2877/10000, Train Loss: 1.3283, Train Accuracy: 0.6060, Val Loss: 1.3589, Val Accuracy: 0.5402 Epoch 2878/10000, Train Loss: 1.3309, Train Accuracy: 0.6060, Val Loss: 1.3588, Val Accuracy: 0.5402 Epoch 2879/10000, Train Loss: 1.3309, Train Accuracy: 0.5949, Val Loss: 1.3587, Val Accuracy: 0.5402 Epoch 2880/10000, Train Loss: 1.3264, Train Accuracy: 0.6038, Val Loss: 1.3587, Val Accuracy: 0.5402 Epoch 2881/10000, Train Loss: 1.3321, Train Accuracy: 0.5949, Val Loss: 1.3586, Val Accuracy: 0.5402 Epoch 2882/10000, Train Loss: 1.3225, Train Accuracy: 0.6138, Val Loss: 1.3585, Val Accuracy: 0.5402 Epoch 2883/10000, Train Loss: 1.3267, Train Accuracy: 0.6049, Val Loss: 1.3584, Val Accuracy: 0.5402 Epoch 2884/10000, Train Loss: 1.3270, Train Accuracy: 0.6060, Val Loss: 1.3583, Val Accuracy: 0.5402 Epoch 2885/10000, Train Loss: 1.3296, Train Accuracy: 0.5960, Val Loss: 1.3583, Val Accuracy: 0.5402 Epoch 2886/10000, Train Loss: 1.3290, Train Accuracy: 0.6094, Val Loss: 1.3581, Val Accuracy: 0.5402 Epoch 2887/10000, Train Loss: 1.3224, Train Accuracy: 0.6138, Val Loss: 1.3581, Val Accuracy: 0.5402 Epoch 2888/10000, Train Loss: 1.3230, Train Accuracy: 0.6027, Val Loss: 1.3580, Val Accuracy: 0.5402 Epoch 2889/10000, Train Loss: 1.3212, Train Accuracy: 0.6138, Val Loss: 1.3579, Val Accuracy: 0.5402 Epoch 2890/10000, Train Loss: 1.3225, Train Accuracy: 0.6127, Val Loss: 1.3579, Val Accuracy: 0.5402 Epoch 2891/10000, Train Loss: 1.3229, Train Accuracy: 0.6004, Val Loss: 1.3578, Val Accuracy: 0.5402 Epoch 2892/10000, Train Loss: 1.3265, Train Accuracy: 0.6027, Val Loss: 1.3578, Val Accuracy: 0.5402 Epoch 2893/10000, Train Loss: 1.3196, Train Accuracy: 0.6228, Val Loss: 1.3577, Val Accuracy: 0.5402 Epoch 2894/10000, Train Loss: 1.3332, Train Accuracy: 0.5882, Val Loss: 1.3575, Val Accuracy: 0.5402 Epoch 2895/10000, Train Loss: 1.3304, Train Accuracy: 0.6027, Val Loss: 1.3575, Val Accuracy: 0.5402 Epoch 2896/10000, Train Loss: 1.3282, Train Accuracy: 0.6138, Val Loss: 1.3574, Val Accuracy: 0.5402 Epoch 2897/10000, Train Loss: 1.3224, Train Accuracy: 0.6071, Val Loss: 1.3574, Val Accuracy: 0.5402 Epoch 2898/10000, Train Loss: 1.3222, Train Accuracy: 0.6116, Val Loss: 1.3573, Val Accuracy: 0.5402 Epoch 2899/10000, Train Loss: 1.3141, Train Accuracy: 0.6283, Val Loss: 1.3572, Val Accuracy: 0.5402 Epoch 2900/10000, Train Loss: 1.3129, Train Accuracy: 0.6295, Val Loss: 1.3571, Val Accuracy: 0.5402 Epoch 2901/10000, Train Loss: 1.3287, Train Accuracy: 0.5904, Val Loss: 1.3571, Val Accuracy: 0.5402 Epoch 2902/10000, Train Loss: 1.3215, Train Accuracy: 0.6094, Val Loss: 1.3569, Val Accuracy: 0.5402 Epoch 2903/10000, Train Loss: 1.3293, Train Accuracy: 0.6071, Val Loss: 1.3569, Val Accuracy: 0.5402 Epoch 2904/10000, Train Loss: 1.3180, Train Accuracy: 0.6172, Val Loss: 1.3568, Val Accuracy: 0.5402 Epoch 2905/10000, Train Loss: 1.3209, Train Accuracy: 0.6205, Val Loss: 1.3567, Val Accuracy: 0.5402 Epoch 2906/10000, Train Loss: 1.3167, Train Accuracy: 0.6261, Val Loss: 1.3566, Val Accuracy: 0.5402 Epoch 2907/10000, Train Loss: 1.3230, Train Accuracy: 0.6138, Val Loss: 1.3566, Val Accuracy: 0.5402 Epoch 2908/10000, Train Loss: 1.3264, Train Accuracy: 0.6127, Val Loss: 1.3566, Val Accuracy: 0.5402 Epoch 2909/10000, Train Loss: 1.3186, Train Accuracy: 0.6150, Val Loss: 1.3565, Val Accuracy: 0.5402 Epoch 2910/10000, Train Loss: 1.3293, Train Accuracy: 0.6016, Val Loss: 1.3563, Val Accuracy: 0.5402 Epoch 2911/10000, Train Loss: 1.3292, Train Accuracy: 0.6016, Val Loss: 1.3563, Val Accuracy: 0.5402 Epoch 2912/10000, Train Loss: 1.3280, Train Accuracy: 0.6071, Val Loss: 1.3561, Val Accuracy: 0.5402 Epoch 2913/10000, Train Loss: 1.3250, Train Accuracy: 0.6083, Val Loss: 1.3561, Val Accuracy: 0.5402 Epoch 2914/10000, Train Loss: 1.3183, Train Accuracy: 0.6217, Val Loss: 1.3560, Val Accuracy: 0.5402 Epoch 2915/10000, Train Loss: 1.3129, Train Accuracy: 0.6306, Val Loss: 1.3559, Val Accuracy: 0.5402 Epoch 2916/10000, Train Loss: 1.3170, Train Accuracy: 0.6272, Val Loss: 1.3559, Val Accuracy: 0.5402 Epoch 2917/10000, Train Loss: 1.3144, Train Accuracy: 0.6172, Val Loss: 1.3558, Val Accuracy: 0.5402 Epoch 2918/10000, Train Loss: 1.3191, Train Accuracy: 0.6105, Val Loss: 1.3557, Val Accuracy: 0.5402 Epoch 2919/10000, Train Loss: 1.3217, Train Accuracy: 0.6138, Val Loss: 1.3557, Val Accuracy: 0.5402 Epoch 2920/10000, Train Loss: 1.3193, Train Accuracy: 0.6161, Val Loss: 1.3555, Val Accuracy: 0.5402 Epoch 2921/10000, Train Loss: 1.3209, Train Accuracy: 0.6205, Val Loss: 1.3555, Val Accuracy: 0.5402 Epoch 2922/10000, Train Loss: 1.3079, Train Accuracy: 0.6194, Val Loss: 1.3554, Val Accuracy: 0.5402 Epoch 2923/10000, Train Loss: 1.3073, Train Accuracy: 0.6250, Val Loss: 1.3553, Val Accuracy: 0.5402 Epoch 2924/10000, Train Loss: 1.3248, Train Accuracy: 0.6071, Val Loss: 1.3552, Val Accuracy: 0.5402 Epoch 2925/10000, Train Loss: 1.3155, Train Accuracy: 0.6339, Val Loss: 1.3551, Val Accuracy: 0.5402 Epoch 2926/10000, Train Loss: 1.3126, Train Accuracy: 0.6283, Val Loss: 1.3550, Val Accuracy: 0.5402 Epoch 2927/10000, Train Loss: 1.3270, Train Accuracy: 0.6138, Val Loss: 1.3549, Val Accuracy: 0.5402 Epoch 2928/10000, Train Loss: 1.3291, Train Accuracy: 0.6004, Val Loss: 1.3548, Val Accuracy: 0.5402 Epoch 2929/10000, Train Loss: 1.3265, Train Accuracy: 0.5993, Val Loss: 1.3547, Val Accuracy: 0.5402 Epoch 2930/10000, Train Loss: 1.3264, Train Accuracy: 0.6060, Val Loss: 1.3546, Val Accuracy: 0.5402 Epoch 2931/10000, Train Loss: 1.3232, Train Accuracy: 0.6205, Val Loss: 1.3546, Val Accuracy: 0.5402 Epoch 2932/10000, Train Loss: 1.3165, Train Accuracy: 0.6150, Val Loss: 1.3545, Val Accuracy: 0.5402 Epoch 2933/10000, Train Loss: 1.3160, Train Accuracy: 0.6183, Val Loss: 1.3544, Val Accuracy: 0.5402 Epoch 2934/10000, Train Loss: 1.3177, Train Accuracy: 0.6016, Val Loss: 1.3544, Val Accuracy: 0.5402 Epoch 2935/10000, Train Loss: 1.3147, Train Accuracy: 0.6183, Val Loss: 1.3543, Val Accuracy: 0.5402 Epoch 2936/10000, Train Loss: 1.3097, Train Accuracy: 0.6217, Val Loss: 1.3542, Val Accuracy: 0.5402 Epoch 2937/10000, Train Loss: 1.3254, Train Accuracy: 0.5949, Val Loss: 1.3542, Val Accuracy: 0.5402 Epoch 2938/10000, Train Loss: 1.3163, Train Accuracy: 0.6239, Val Loss: 1.3541, Val Accuracy: 0.5402 Epoch 2939/10000, Train Loss: 1.3160, Train Accuracy: 0.6283, Val Loss: 1.3540, Val Accuracy: 0.5402 Epoch 2940/10000, Train Loss: 1.3187, Train Accuracy: 0.6239, Val Loss: 1.3539, Val Accuracy: 0.5402 Epoch 2941/10000, Train Loss: 1.3259, Train Accuracy: 0.6060, Val Loss: 1.3538, Val Accuracy: 0.5402 Epoch 2942/10000, Train Loss: 1.3143, Train Accuracy: 0.6328, Val Loss: 1.3538, Val Accuracy: 0.5402 Epoch 2943/10000, Train Loss: 1.3160, Train Accuracy: 0.6261, Val Loss: 1.3537, Val Accuracy: 0.5402 Epoch 2944/10000, Train Loss: 1.3161, Train Accuracy: 0.6083, Val Loss: 1.3536, Val Accuracy: 0.5402 Epoch 2945/10000, Train Loss: 1.3245, Train Accuracy: 0.5960, Val Loss: 1.3535, Val Accuracy: 0.5402 Epoch 2946/10000, Train Loss: 1.3192, Train Accuracy: 0.6172, Val Loss: 1.3535, Val Accuracy: 0.5402 Epoch 2947/10000, Train Loss: 1.3162, Train Accuracy: 0.6161, Val Loss: 1.3534, Val Accuracy: 0.5402 Epoch 2948/10000, Train Loss: 1.3187, Train Accuracy: 0.6116, Val Loss: 1.3534, Val Accuracy: 0.5402 Epoch 2949/10000, Train Loss: 1.3200, Train Accuracy: 0.6038, Val Loss: 1.3533, Val Accuracy: 0.5446 Epoch 2950/10000, Train Loss: 1.3248, Train Accuracy: 0.6027, Val Loss: 1.3532, Val Accuracy: 0.5446 Epoch 2951/10000, Train Loss: 1.3197, Train Accuracy: 0.6049, Val Loss: 1.3532, Val Accuracy: 0.5446 Epoch 2952/10000, Train Loss: 1.3099, Train Accuracy: 0.6406, Val Loss: 1.3531, Val Accuracy: 0.5446 Epoch 2953/10000, Train Loss: 1.3192, Train Accuracy: 0.6261, Val Loss: 1.3530, Val Accuracy: 0.5446 Epoch 2954/10000, Train Loss: 1.3151, Train Accuracy: 0.6205, Val Loss: 1.3529, Val Accuracy: 0.5446 Epoch 2955/10000, Train Loss: 1.3173, Train Accuracy: 0.6038, Val Loss: 1.3529, Val Accuracy: 0.5446 Epoch 2956/10000, Train Loss: 1.3251, Train Accuracy: 0.5960, Val Loss: 1.3528, Val Accuracy: 0.5446 Epoch 2957/10000, Train Loss: 1.3151, Train Accuracy: 0.6161, Val Loss: 1.3527, Val Accuracy: 0.5446 Epoch 2958/10000, Train Loss: 1.3071, Train Accuracy: 0.6339, Val Loss: 1.3527, Val Accuracy: 0.5446 Epoch 2959/10000, Train Loss: 1.3192, Train Accuracy: 0.6116, Val Loss: 1.3526, Val Accuracy: 0.5446 Epoch 2960/10000, Train Loss: 1.3201, Train Accuracy: 0.6138, Val Loss: 1.3525, Val Accuracy: 0.5446 Epoch 2961/10000, Train Loss: 1.3085, Train Accuracy: 0.6306, Val Loss: 1.3524, Val Accuracy: 0.5446 Epoch 2962/10000, Train Loss: 1.3138, Train Accuracy: 0.6217, Val Loss: 1.3523, Val Accuracy: 0.5446 Epoch 2963/10000, Train Loss: 1.3081, Train Accuracy: 0.6272, Val Loss: 1.3522, Val Accuracy: 0.5402 Epoch 2964/10000, Train Loss: 1.3133, Train Accuracy: 0.6250, Val Loss: 1.3522, Val Accuracy: 0.5402 Epoch 2965/10000, Train Loss: 1.3224, Train Accuracy: 0.6172, Val Loss: 1.3522, Val Accuracy: 0.5446 Epoch 2966/10000, Train Loss: 1.3126, Train Accuracy: 0.6172, Val Loss: 1.3521, Val Accuracy: 0.5402 Epoch 2967/10000, Train Loss: 1.3134, Train Accuracy: 0.6016, Val Loss: 1.3520, Val Accuracy: 0.5402 Epoch 2968/10000, Train Loss: 1.3203, Train Accuracy: 0.6049, Val Loss: 1.3519, Val Accuracy: 0.5446 Epoch 2969/10000, Train Loss: 1.3182, Train Accuracy: 0.6150, Val Loss: 1.3519, Val Accuracy: 0.5446 Epoch 2970/10000, Train Loss: 1.3140, Train Accuracy: 0.6272, Val Loss: 1.3518, Val Accuracy: 0.5446 Epoch 2971/10000, Train Loss: 1.3150, Train Accuracy: 0.6228, Val Loss: 1.3518, Val Accuracy: 0.5446 Epoch 2972/10000, Train Loss: 1.3148, Train Accuracy: 0.6161, Val Loss: 1.3518, Val Accuracy: 0.5446 Epoch 2973/10000, Train Loss: 1.3111, Train Accuracy: 0.6250, Val Loss: 1.3516, Val Accuracy: 0.5446 Epoch 2974/10000, Train Loss: 1.3195, Train Accuracy: 0.6038, Val Loss: 1.3515, Val Accuracy: 0.5446 Epoch 2975/10000, Train Loss: 1.3130, Train Accuracy: 0.6283, Val Loss: 1.3515, Val Accuracy: 0.5446 Epoch 2976/10000, Train Loss: 1.3134, Train Accuracy: 0.6138, Val Loss: 1.3514, Val Accuracy: 0.5446 Epoch 2977/10000, Train Loss: 1.3091, Train Accuracy: 0.6339, Val Loss: 1.3514, Val Accuracy: 0.5446 Epoch 2978/10000, Train Loss: 1.3229, Train Accuracy: 0.5949, Val Loss: 1.3512, Val Accuracy: 0.5446 Epoch 2979/10000, Train Loss: 1.3067, Train Accuracy: 0.6384, Val Loss: 1.3512, Val Accuracy: 0.5402 Epoch 2980/10000, Train Loss: 1.3123, Train Accuracy: 0.6317, Val Loss: 1.3511, Val Accuracy: 0.5402 Epoch 2981/10000, Train Loss: 1.3159, Train Accuracy: 0.6239, Val Loss: 1.3511, Val Accuracy: 0.5402 Epoch 2982/10000, Train Loss: 1.3042, Train Accuracy: 0.6272, Val Loss: 1.3510, Val Accuracy: 0.5446 Epoch 2983/10000, Train Loss: 1.3108, Train Accuracy: 0.6183, Val Loss: 1.3508, Val Accuracy: 0.5446 Epoch 2984/10000, Train Loss: 1.3130, Train Accuracy: 0.6172, Val Loss: 1.3508, Val Accuracy: 0.5446 Epoch 2985/10000, Train Loss: 1.3139, Train Accuracy: 0.6083, Val Loss: 1.3507, Val Accuracy: 0.5446 Epoch 2986/10000, Train Loss: 1.2997, Train Accuracy: 0.6484, Val Loss: 1.3506, Val Accuracy: 0.5446 Epoch 2987/10000, Train Loss: 1.3102, Train Accuracy: 0.6172, Val Loss: 1.3505, Val Accuracy: 0.5446 Epoch 2988/10000, Train Loss: 1.3147, Train Accuracy: 0.6060, Val Loss: 1.3505, Val Accuracy: 0.5446 Epoch 2989/10000, Train Loss: 1.3156, Train Accuracy: 0.6027, Val Loss: 1.3504, Val Accuracy: 0.5446 Epoch 2990/10000, Train Loss: 1.3141, Train Accuracy: 0.6183, Val Loss: 1.3503, Val Accuracy: 0.5446 Epoch 2991/10000, Train Loss: 1.3193, Train Accuracy: 0.6138, Val Loss: 1.3502, Val Accuracy: 0.5446 Epoch 2992/10000, Train Loss: 1.3204, Train Accuracy: 0.6049, Val Loss: 1.3501, Val Accuracy: 0.5446 Epoch 2993/10000, Train Loss: 1.3136, Train Accuracy: 0.6261, Val Loss: 1.3500, Val Accuracy: 0.5446 Epoch 2994/10000, Train Loss: 1.3068, Train Accuracy: 0.6228, Val Loss: 1.3499, Val Accuracy: 0.5446 Epoch 2995/10000, Train Loss: 1.3053, Train Accuracy: 0.6306, Val Loss: 1.3499, Val Accuracy: 0.5446 Epoch 2996/10000, Train Loss: 1.3194, Train Accuracy: 0.6172, Val Loss: 1.3497, Val Accuracy: 0.5446 Epoch 2997/10000, Train Loss: 1.3101, Train Accuracy: 0.6183, Val Loss: 1.3497, Val Accuracy: 0.5446 Epoch 2998/10000, Train Loss: 1.3201, Train Accuracy: 0.6071, Val Loss: 1.3496, Val Accuracy: 0.5446 Epoch 2999/10000, Train Loss: 1.3151, Train Accuracy: 0.6161, Val Loss: 1.3496, Val Accuracy: 0.5446 Epoch 3000/10000, Train Loss: 1.3115, Train Accuracy: 0.6250, Val Loss: 1.3496, Val Accuracy: 0.5446 Epoch 3001/10000, Train Loss: 1.3049, Train Accuracy: 0.6317, Val Loss: 1.3494, Val Accuracy: 0.5446 Epoch 3002/10000, Train Loss: 1.3084, Train Accuracy: 0.6205, Val Loss: 1.3493, Val Accuracy: 0.5446 Epoch 3003/10000, Train Loss: 1.3108, Train Accuracy: 0.6161, Val Loss: 1.3493, Val Accuracy: 0.5446 Epoch 3004/10000, Train Loss: 1.3104, Train Accuracy: 0.6272, Val Loss: 1.3493, Val Accuracy: 0.5402 Epoch 3005/10000, Train Loss: 1.3137, Train Accuracy: 0.6172, Val Loss: 1.3492, Val Accuracy: 0.5402 Epoch 3006/10000, Train Loss: 1.3120, Train Accuracy: 0.6250, Val Loss: 1.3491, Val Accuracy: 0.5402 Epoch 3007/10000, Train Loss: 1.3155, Train Accuracy: 0.6183, Val Loss: 1.3490, Val Accuracy: 0.5402 Epoch 3008/10000, Train Loss: 1.3099, Train Accuracy: 0.6194, Val Loss: 1.3490, Val Accuracy: 0.5402 Epoch 3009/10000, Train Loss: 1.3166, Train Accuracy: 0.6027, Val Loss: 1.3489, Val Accuracy: 0.5402 Epoch 3010/10000, Train Loss: 1.3086, Train Accuracy: 0.6161, Val Loss: 1.3489, Val Accuracy: 0.5402 Epoch 3011/10000, Train Loss: 1.3119, Train Accuracy: 0.6183, Val Loss: 1.3488, Val Accuracy: 0.5402 Epoch 3012/10000, Train Loss: 1.3182, Train Accuracy: 0.6094, Val Loss: 1.3488, Val Accuracy: 0.5402 Epoch 3013/10000, Train Loss: 1.3156, Train Accuracy: 0.6250, Val Loss: 1.3487, Val Accuracy: 0.5402 Epoch 3014/10000, Train Loss: 1.3136, Train Accuracy: 0.6217, Val Loss: 1.3487, Val Accuracy: 0.5446 Epoch 3015/10000, Train Loss: 1.3099, Train Accuracy: 0.6350, Val Loss: 1.3486, Val Accuracy: 0.5446 Epoch 3016/10000, Train Loss: 1.3104, Train Accuracy: 0.6228, Val Loss: 1.3485, Val Accuracy: 0.5446 Epoch 3017/10000, Train Loss: 1.3139, Train Accuracy: 0.6127, Val Loss: 1.3484, Val Accuracy: 0.5446 Epoch 3018/10000, Train Loss: 1.3180, Train Accuracy: 0.6239, Val Loss: 1.3484, Val Accuracy: 0.5491 Epoch 3019/10000, Train Loss: 1.3192, Train Accuracy: 0.6105, Val Loss: 1.3483, Val Accuracy: 0.5446 Epoch 3020/10000, Train Loss: 1.3134, Train Accuracy: 0.6172, Val Loss: 1.3482, Val Accuracy: 0.5491 Epoch 3021/10000, Train Loss: 1.3173, Train Accuracy: 0.6217, Val Loss: 1.3482, Val Accuracy: 0.5491 Epoch 3022/10000, Train Loss: 1.3114, Train Accuracy: 0.6194, Val Loss: 1.3482, Val Accuracy: 0.5491 Epoch 3023/10000, Train Loss: 1.3107, Train Accuracy: 0.6150, Val Loss: 1.3481, Val Accuracy: 0.5491 Epoch 3024/10000, Train Loss: 1.3077, Train Accuracy: 0.6306, Val Loss: 1.3481, Val Accuracy: 0.5491 Epoch 3025/10000, Train Loss: 1.3055, Train Accuracy: 0.6261, Val Loss: 1.3481, Val Accuracy: 0.5491 Epoch 3026/10000, Train Loss: 1.3062, Train Accuracy: 0.6283, Val Loss: 1.3479, Val Accuracy: 0.5491 Epoch 3027/10000, Train Loss: 1.3097, Train Accuracy: 0.6250, Val Loss: 1.3478, Val Accuracy: 0.5491 Epoch 3028/10000, Train Loss: 1.2964, Train Accuracy: 0.6473, Val Loss: 1.3478, Val Accuracy: 0.5491 Epoch 3029/10000, Train Loss: 1.3078, Train Accuracy: 0.6194, Val Loss: 1.3476, Val Accuracy: 0.5491 Epoch 3030/10000, Train Loss: 1.3164, Train Accuracy: 0.6060, Val Loss: 1.3476, Val Accuracy: 0.5491 Epoch 3031/10000, Train Loss: 1.3117, Train Accuracy: 0.6217, Val Loss: 1.3475, Val Accuracy: 0.5491 Epoch 3032/10000, Train Loss: 1.3090, Train Accuracy: 0.6194, Val Loss: 1.3475, Val Accuracy: 0.5491 Epoch 3033/10000, Train Loss: 1.2963, Train Accuracy: 0.6529, Val Loss: 1.3474, Val Accuracy: 0.5491 Epoch 3034/10000, Train Loss: 1.3074, Train Accuracy: 0.6261, Val Loss: 1.3472, Val Accuracy: 0.5491 Epoch 3035/10000, Train Loss: 1.2983, Train Accuracy: 0.6350, Val Loss: 1.3471, Val Accuracy: 0.5491 Epoch 3036/10000, Train Loss: 1.3023, Train Accuracy: 0.6283, Val Loss: 1.3471, Val Accuracy: 0.5491 Epoch 3037/10000, Train Loss: 1.3119, Train Accuracy: 0.6283, Val Loss: 1.3470, Val Accuracy: 0.5491 Epoch 3038/10000, Train Loss: 1.3094, Train Accuracy: 0.6283, Val Loss: 1.3469, Val Accuracy: 0.5491 Epoch 3039/10000, Train Loss: 1.3081, Train Accuracy: 0.6261, Val Loss: 1.3468, Val Accuracy: 0.5491 Epoch 3040/10000, Train Loss: 1.3099, Train Accuracy: 0.6272, Val Loss: 1.3468, Val Accuracy: 0.5491 Epoch 3041/10000, Train Loss: 1.3002, Train Accuracy: 0.6339, Val Loss: 1.3467, Val Accuracy: 0.5491 Epoch 3042/10000, Train Loss: 1.3124, Train Accuracy: 0.6105, Val Loss: 1.3466, Val Accuracy: 0.5491 Epoch 3043/10000, Train Loss: 1.3141, Train Accuracy: 0.6217, Val Loss: 1.3465, Val Accuracy: 0.5491 Epoch 3044/10000, Train Loss: 1.3047, Train Accuracy: 0.6406, Val Loss: 1.3464, Val Accuracy: 0.5491 Epoch 3045/10000, Train Loss: 1.3014, Train Accuracy: 0.6295, Val Loss: 1.3463, Val Accuracy: 0.5491 Epoch 3046/10000, Train Loss: 1.3058, Train Accuracy: 0.6161, Val Loss: 1.3463, Val Accuracy: 0.5491 Epoch 3047/10000, Train Loss: 1.3029, Train Accuracy: 0.6183, Val Loss: 1.3462, Val Accuracy: 0.5491 Epoch 3048/10000, Train Loss: 1.3070, Train Accuracy: 0.6373, Val Loss: 1.3462, Val Accuracy: 0.5491 Epoch 3049/10000, Train Loss: 1.3050, Train Accuracy: 0.6283, Val Loss: 1.3462, Val Accuracy: 0.5491 Epoch 3050/10000, Train Loss: 1.3067, Train Accuracy: 0.6217, Val Loss: 1.3460, Val Accuracy: 0.5491 Epoch 3051/10000, Train Loss: 1.3038, Train Accuracy: 0.6272, Val Loss: 1.3459, Val Accuracy: 0.5491 Epoch 3052/10000, Train Loss: 1.3132, Train Accuracy: 0.6172, Val Loss: 1.3459, Val Accuracy: 0.5491 Epoch 3053/10000, Train Loss: 1.3036, Train Accuracy: 0.6362, Val Loss: 1.3458, Val Accuracy: 0.5491 Epoch 3054/10000, Train Loss: 1.3048, Train Accuracy: 0.6451, Val Loss: 1.3457, Val Accuracy: 0.5491 Epoch 3055/10000, Train Loss: 1.2980, Train Accuracy: 0.6306, Val Loss: 1.3457, Val Accuracy: 0.5491 Epoch 3056/10000, Train Loss: 1.3023, Train Accuracy: 0.6272, Val Loss: 1.3457, Val Accuracy: 0.5491 Epoch 3057/10000, Train Loss: 1.3075, Train Accuracy: 0.6350, Val Loss: 1.3455, Val Accuracy: 0.5491 Epoch 3058/10000, Train Loss: 1.3004, Train Accuracy: 0.6406, Val Loss: 1.3456, Val Accuracy: 0.5491 Epoch 3059/10000, Train Loss: 1.3108, Train Accuracy: 0.6194, Val Loss: 1.3454, Val Accuracy: 0.5491 Epoch 3060/10000, Train Loss: 1.3003, Train Accuracy: 0.6295, Val Loss: 1.3453, Val Accuracy: 0.5491 Epoch 3061/10000, Train Loss: 1.2988, Train Accuracy: 0.6239, Val Loss: 1.3452, Val Accuracy: 0.5491 Epoch 3062/10000, Train Loss: 1.3039, Train Accuracy: 0.6350, Val Loss: 1.3451, Val Accuracy: 0.5491 Epoch 3063/10000, Train Loss: 1.3114, Train Accuracy: 0.6272, Val Loss: 1.3451, Val Accuracy: 0.5491 Epoch 3064/10000, Train Loss: 1.3091, Train Accuracy: 0.6183, Val Loss: 1.3449, Val Accuracy: 0.5491 Epoch 3065/10000, Train Loss: 1.3073, Train Accuracy: 0.6283, Val Loss: 1.3449, Val Accuracy: 0.5491 Epoch 3066/10000, Train Loss: 1.3040, Train Accuracy: 0.6317, Val Loss: 1.3448, Val Accuracy: 0.5491 Epoch 3067/10000, Train Loss: 1.3085, Train Accuracy: 0.6138, Val Loss: 1.3447, Val Accuracy: 0.5491 Epoch 3068/10000, Train Loss: 1.3051, Train Accuracy: 0.6250, Val Loss: 1.3446, Val Accuracy: 0.5491 Epoch 3069/10000, Train Loss: 1.3041, Train Accuracy: 0.6328, Val Loss: 1.3447, Val Accuracy: 0.5491 Epoch 3070/10000, Train Loss: 1.2906, Train Accuracy: 0.6451, Val Loss: 1.3446, Val Accuracy: 0.5491 Epoch 3071/10000, Train Loss: 1.3012, Train Accuracy: 0.6261, Val Loss: 1.3445, Val Accuracy: 0.5491 Epoch 3072/10000, Train Loss: 1.3188, Train Accuracy: 0.6038, Val Loss: 1.3444, Val Accuracy: 0.5491 Epoch 3073/10000, Train Loss: 1.3089, Train Accuracy: 0.6362, Val Loss: 1.3443, Val Accuracy: 0.5491 Epoch 3074/10000, Train Loss: 1.3086, Train Accuracy: 0.6239, Val Loss: 1.3443, Val Accuracy: 0.5491 Epoch 3075/10000, Train Loss: 1.2953, Train Accuracy: 0.6350, Val Loss: 1.3443, Val Accuracy: 0.5491 Epoch 3076/10000, Train Loss: 1.3054, Train Accuracy: 0.6261, Val Loss: 1.3442, Val Accuracy: 0.5491 Epoch 3077/10000, Train Loss: 1.3003, Train Accuracy: 0.6194, Val Loss: 1.3440, Val Accuracy: 0.5491 Epoch 3078/10000, Train Loss: 1.3134, Train Accuracy: 0.6116, Val Loss: 1.3440, Val Accuracy: 0.5491 Epoch 3079/10000, Train Loss: 1.2968, Train Accuracy: 0.6496, Val Loss: 1.3439, Val Accuracy: 0.5491 Epoch 3080/10000, Train Loss: 1.3000, Train Accuracy: 0.6384, Val Loss: 1.3438, Val Accuracy: 0.5491 Epoch 3081/10000, Train Loss: 1.3159, Train Accuracy: 0.6127, Val Loss: 1.3437, Val Accuracy: 0.5491 Epoch 3082/10000, Train Loss: 1.3044, Train Accuracy: 0.6205, Val Loss: 1.3436, Val Accuracy: 0.5491 Epoch 3083/10000, Train Loss: 1.3140, Train Accuracy: 0.6083, Val Loss: 1.3436, Val Accuracy: 0.5491 Epoch 3084/10000, Train Loss: 1.3119, Train Accuracy: 0.6217, Val Loss: 1.3435, Val Accuracy: 0.5491 Epoch 3085/10000, Train Loss: 1.3048, Train Accuracy: 0.6239, Val Loss: 1.3434, Val Accuracy: 0.5491 Epoch 3086/10000, Train Loss: 1.2996, Train Accuracy: 0.6150, Val Loss: 1.3434, Val Accuracy: 0.5491 Epoch 3087/10000, Train Loss: 1.3053, Train Accuracy: 0.6138, Val Loss: 1.3433, Val Accuracy: 0.5491 Epoch 3088/10000, Train Loss: 1.2964, Train Accuracy: 0.6295, Val Loss: 1.3433, Val Accuracy: 0.5491 Epoch 3089/10000, Train Loss: 1.2966, Train Accuracy: 0.6283, Val Loss: 1.3431, Val Accuracy: 0.5491 Epoch 3090/10000, Train Loss: 1.3076, Train Accuracy: 0.6295, Val Loss: 1.3431, Val Accuracy: 0.5491 Epoch 3091/10000, Train Loss: 1.3154, Train Accuracy: 0.6083, Val Loss: 1.3430, Val Accuracy: 0.5491 Epoch 3092/10000, Train Loss: 1.2983, Train Accuracy: 0.6317, Val Loss: 1.3429, Val Accuracy: 0.5491 Epoch 3093/10000, Train Loss: 1.3023, Train Accuracy: 0.6161, Val Loss: 1.3428, Val Accuracy: 0.5491 Epoch 3094/10000, Train Loss: 1.3031, Train Accuracy: 0.6205, Val Loss: 1.3427, Val Accuracy: 0.5491 Epoch 3095/10000, Train Loss: 1.3073, Train Accuracy: 0.6239, Val Loss: 1.3427, Val Accuracy: 0.5491 Epoch 3096/10000, Train Loss: 1.3087, Train Accuracy: 0.6250, Val Loss: 1.3426, Val Accuracy: 0.5491 Epoch 3097/10000, Train Loss: 1.3015, Train Accuracy: 0.6205, Val Loss: 1.3425, Val Accuracy: 0.5491 Epoch 3098/10000, Train Loss: 1.2991, Train Accuracy: 0.6317, Val Loss: 1.3425, Val Accuracy: 0.5536 Epoch 3099/10000, Train Loss: 1.2970, Train Accuracy: 0.6384, Val Loss: 1.3424, Val Accuracy: 0.5536 Epoch 3100/10000, Train Loss: 1.2980, Train Accuracy: 0.6317, Val Loss: 1.3424, Val Accuracy: 0.5536 Epoch 3101/10000, Train Loss: 1.3138, Train Accuracy: 0.6161, Val Loss: 1.3424, Val Accuracy: 0.5536 Epoch 3102/10000, Train Loss: 1.2980, Train Accuracy: 0.6384, Val Loss: 1.3424, Val Accuracy: 0.5536 Epoch 3103/10000, Train Loss: 1.2980, Train Accuracy: 0.6217, Val Loss: 1.3423, Val Accuracy: 0.5536 Epoch 3104/10000, Train Loss: 1.2961, Train Accuracy: 0.6451, Val Loss: 1.3422, Val Accuracy: 0.5536 Epoch 3105/10000, Train Loss: 1.3029, Train Accuracy: 0.6350, Val Loss: 1.3422, Val Accuracy: 0.5536 Epoch 3106/10000, Train Loss: 1.3058, Train Accuracy: 0.6362, Val Loss: 1.3421, Val Accuracy: 0.5536 Epoch 3107/10000, Train Loss: 1.3021, Train Accuracy: 0.6272, Val Loss: 1.3420, Val Accuracy: 0.5536 Epoch 3108/10000, Train Loss: 1.2946, Train Accuracy: 0.6261, Val Loss: 1.3420, Val Accuracy: 0.5536 Epoch 3109/10000, Train Loss: 1.2947, Train Accuracy: 0.6440, Val Loss: 1.3418, Val Accuracy: 0.5536 Epoch 3110/10000, Train Loss: 1.2978, Train Accuracy: 0.6484, Val Loss: 1.3418, Val Accuracy: 0.5536 Epoch 3111/10000, Train Loss: 1.2954, Train Accuracy: 0.6429, Val Loss: 1.3417, Val Accuracy: 0.5536 Epoch 3112/10000, Train Loss: 1.2975, Train Accuracy: 0.6362, Val Loss: 1.3417, Val Accuracy: 0.5536 Epoch 3113/10000, Train Loss: 1.3075, Train Accuracy: 0.6239, Val Loss: 1.3416, Val Accuracy: 0.5536 Epoch 3114/10000, Train Loss: 1.3017, Train Accuracy: 0.6217, Val Loss: 1.3415, Val Accuracy: 0.5536 Epoch 3115/10000, Train Loss: 1.2913, Train Accuracy: 0.6451, Val Loss: 1.3415, Val Accuracy: 0.5536 Epoch 3116/10000, Train Loss: 1.2994, Train Accuracy: 0.6350, Val Loss: 1.3415, Val Accuracy: 0.5536 Epoch 3117/10000, Train Loss: 1.2923, Train Accuracy: 0.6395, Val Loss: 1.3414, Val Accuracy: 0.5536 Epoch 3118/10000, Train Loss: 1.3095, Train Accuracy: 0.6228, Val Loss: 1.3413, Val Accuracy: 0.5536 Epoch 3119/10000, Train Loss: 1.2887, Train Accuracy: 0.6373, Val Loss: 1.3412, Val Accuracy: 0.5536 Epoch 3120/10000, Train Loss: 1.3019, Train Accuracy: 0.6317, Val Loss: 1.3411, Val Accuracy: 0.5536 Epoch 3121/10000, Train Loss: 1.3067, Train Accuracy: 0.6261, Val Loss: 1.3410, Val Accuracy: 0.5536 Epoch 3122/10000, Train Loss: 1.3000, Train Accuracy: 0.6172, Val Loss: 1.3411, Val Accuracy: 0.5536 Epoch 3123/10000, Train Loss: 1.2948, Train Accuracy: 0.6362, Val Loss: 1.3410, Val Accuracy: 0.5536 Epoch 3124/10000, Train Loss: 1.2946, Train Accuracy: 0.6417, Val Loss: 1.3409, Val Accuracy: 0.5536 Epoch 3125/10000, Train Loss: 1.2983, Train Accuracy: 0.6228, Val Loss: 1.3409, Val Accuracy: 0.5536 Epoch 3126/10000, Train Loss: 1.3021, Train Accuracy: 0.6261, Val Loss: 1.3408, Val Accuracy: 0.5536 Epoch 3127/10000, Train Loss: 1.2979, Train Accuracy: 0.6362, Val Loss: 1.3407, Val Accuracy: 0.5536 Epoch 3128/10000, Train Loss: 1.2994, Train Accuracy: 0.6306, Val Loss: 1.3407, Val Accuracy: 0.5536 Epoch 3129/10000, Train Loss: 1.2984, Train Accuracy: 0.6306, Val Loss: 1.3406, Val Accuracy: 0.5536 Epoch 3130/10000, Train Loss: 1.2972, Train Accuracy: 0.6451, Val Loss: 1.3406, Val Accuracy: 0.5536 Epoch 3131/10000, Train Loss: 1.2940, Train Accuracy: 0.6373, Val Loss: 1.3405, Val Accuracy: 0.5536 Epoch 3132/10000, Train Loss: 1.3070, Train Accuracy: 0.6228, Val Loss: 1.3404, Val Accuracy: 0.5536 Epoch 3133/10000, Train Loss: 1.2982, Train Accuracy: 0.6250, Val Loss: 1.3403, Val Accuracy: 0.5536 Epoch 3134/10000, Train Loss: 1.2924, Train Accuracy: 0.6362, Val Loss: 1.3402, Val Accuracy: 0.5536 Epoch 3135/10000, Train Loss: 1.2982, Train Accuracy: 0.6250, Val Loss: 1.3402, Val Accuracy: 0.5536 Epoch 3136/10000, Train Loss: 1.3029, Train Accuracy: 0.6239, Val Loss: 1.3401, Val Accuracy: 0.5536 Epoch 3137/10000, Train Loss: 1.2900, Train Accuracy: 0.6417, Val Loss: 1.3400, Val Accuracy: 0.5536 Epoch 3138/10000, Train Loss: 1.2998, Train Accuracy: 0.6272, Val Loss: 1.3399, Val Accuracy: 0.5536 Epoch 3139/10000, Train Loss: 1.2969, Train Accuracy: 0.6429, Val Loss: 1.3398, Val Accuracy: 0.5536 Epoch 3140/10000, Train Loss: 1.2890, Train Accuracy: 0.6462, Val Loss: 1.3398, Val Accuracy: 0.5536 Epoch 3141/10000, Train Loss: 1.2917, Train Accuracy: 0.6473, Val Loss: 1.3397, Val Accuracy: 0.5536 Epoch 3142/10000, Train Loss: 1.3024, Train Accuracy: 0.6228, Val Loss: 1.3396, Val Accuracy: 0.5536 Epoch 3143/10000, Train Loss: 1.2960, Train Accuracy: 0.6417, Val Loss: 1.3396, Val Accuracy: 0.5536 Epoch 3144/10000, Train Loss: 1.2962, Train Accuracy: 0.6395, Val Loss: 1.3395, Val Accuracy: 0.5536 Epoch 3145/10000, Train Loss: 1.2981, Train Accuracy: 0.6205, Val Loss: 1.3394, Val Accuracy: 0.5536 Epoch 3146/10000, Train Loss: 1.2970, Train Accuracy: 0.6239, Val Loss: 1.3393, Val Accuracy: 0.5536 Epoch 3147/10000, Train Loss: 1.2904, Train Accuracy: 0.6473, Val Loss: 1.3392, Val Accuracy: 0.5536 Epoch 3148/10000, Train Loss: 1.2894, Train Accuracy: 0.6484, Val Loss: 1.3391, Val Accuracy: 0.5536 Epoch 3149/10000, Train Loss: 1.2903, Train Accuracy: 0.6440, Val Loss: 1.3390, Val Accuracy: 0.5536 Epoch 3150/10000, Train Loss: 1.2910, Train Accuracy: 0.6261, Val Loss: 1.3390, Val Accuracy: 0.5580 Epoch 3151/10000, Train Loss: 1.3075, Train Accuracy: 0.6183, Val Loss: 1.3390, Val Accuracy: 0.5580 Epoch 3152/10000, Train Loss: 1.3012, Train Accuracy: 0.6328, Val Loss: 1.3389, Val Accuracy: 0.5580 Epoch 3153/10000, Train Loss: 1.3027, Train Accuracy: 0.6161, Val Loss: 1.3388, Val Accuracy: 0.5536 Epoch 3154/10000, Train Loss: 1.2957, Train Accuracy: 0.6272, Val Loss: 1.3387, Val Accuracy: 0.5580 Epoch 3155/10000, Train Loss: 1.2940, Train Accuracy: 0.6295, Val Loss: 1.3387, Val Accuracy: 0.5580 Epoch 3156/10000, Train Loss: 1.2997, Train Accuracy: 0.6194, Val Loss: 1.3386, Val Accuracy: 0.5580 Epoch 3157/10000, Train Loss: 1.2920, Train Accuracy: 0.6417, Val Loss: 1.3385, Val Accuracy: 0.5580 Epoch 3158/10000, Train Loss: 1.2911, Train Accuracy: 0.6350, Val Loss: 1.3385, Val Accuracy: 0.5580 Epoch 3159/10000, Train Loss: 1.2927, Train Accuracy: 0.6417, Val Loss: 1.3385, Val Accuracy: 0.5580 Epoch 3160/10000, Train Loss: 1.2927, Train Accuracy: 0.6417, Val Loss: 1.3384, Val Accuracy: 0.5580 Epoch 3161/10000, Train Loss: 1.2937, Train Accuracy: 0.6462, Val Loss: 1.3384, Val Accuracy: 0.5580 Epoch 3162/10000, Train Loss: 1.3043, Train Accuracy: 0.6250, Val Loss: 1.3383, Val Accuracy: 0.5580 Epoch 3163/10000, Train Loss: 1.2935, Train Accuracy: 0.6362, Val Loss: 1.3383, Val Accuracy: 0.5580 Epoch 3164/10000, Train Loss: 1.2922, Train Accuracy: 0.6451, Val Loss: 1.3382, Val Accuracy: 0.5580 Epoch 3165/10000, Train Loss: 1.2969, Train Accuracy: 0.6250, Val Loss: 1.3382, Val Accuracy: 0.5580 Epoch 3166/10000, Train Loss: 1.2908, Train Accuracy: 0.6306, Val Loss: 1.3380, Val Accuracy: 0.5580 Epoch 3167/10000, Train Loss: 1.2953, Train Accuracy: 0.6261, Val Loss: 1.3379, Val Accuracy: 0.5625 Epoch 3168/10000, Train Loss: 1.2874, Train Accuracy: 0.6496, Val Loss: 1.3378, Val Accuracy: 0.5625 Epoch 3169/10000, Train Loss: 1.3066, Train Accuracy: 0.6205, Val Loss: 1.3377, Val Accuracy: 0.5625 Epoch 3170/10000, Train Loss: 1.2894, Train Accuracy: 0.6507, Val Loss: 1.3376, Val Accuracy: 0.5625 Epoch 3171/10000, Train Loss: 1.2880, Train Accuracy: 0.6451, Val Loss: 1.3376, Val Accuracy: 0.5625 Epoch 3172/10000, Train Loss: 1.2888, Train Accuracy: 0.6417, Val Loss: 1.3375, Val Accuracy: 0.5625 Epoch 3173/10000, Train Loss: 1.2926, Train Accuracy: 0.6328, Val Loss: 1.3374, Val Accuracy: 0.5625 Epoch 3174/10000, Train Loss: 1.2907, Train Accuracy: 0.6484, Val Loss: 1.3374, Val Accuracy: 0.5625 Epoch 3175/10000, Train Loss: 1.2841, Train Accuracy: 0.6462, Val Loss: 1.3372, Val Accuracy: 0.5625 Epoch 3176/10000, Train Loss: 1.2905, Train Accuracy: 0.6306, Val Loss: 1.3372, Val Accuracy: 0.5625 Epoch 3177/10000, Train Loss: 1.2806, Train Accuracy: 0.6529, Val Loss: 1.3371, Val Accuracy: 0.5625 Epoch 3178/10000, Train Loss: 1.2942, Train Accuracy: 0.6451, Val Loss: 1.3371, Val Accuracy: 0.5625 Epoch 3179/10000, Train Loss: 1.2946, Train Accuracy: 0.6440, Val Loss: 1.3370, Val Accuracy: 0.5625 Epoch 3180/10000, Train Loss: 1.2925, Train Accuracy: 0.6384, Val Loss: 1.3369, Val Accuracy: 0.5625 Epoch 3181/10000, Train Loss: 1.3013, Train Accuracy: 0.6295, Val Loss: 1.3368, Val Accuracy: 0.5625 Epoch 3182/10000, Train Loss: 1.2909, Train Accuracy: 0.6406, Val Loss: 1.3368, Val Accuracy: 0.5625 Epoch 3183/10000, Train Loss: 1.2890, Train Accuracy: 0.6618, Val Loss: 1.3367, Val Accuracy: 0.5625 Epoch 3184/10000, Train Loss: 1.2930, Train Accuracy: 0.6295, Val Loss: 1.3367, Val Accuracy: 0.5625 Epoch 3185/10000, Train Loss: 1.2836, Train Accuracy: 0.6529, Val Loss: 1.3367, Val Accuracy: 0.5625 Epoch 3186/10000, Train Loss: 1.2906, Train Accuracy: 0.6417, Val Loss: 1.3366, Val Accuracy: 0.5670 Epoch 3187/10000, Train Loss: 1.2832, Train Accuracy: 0.6529, Val Loss: 1.3365, Val Accuracy: 0.5670 Epoch 3188/10000, Train Loss: 1.2956, Train Accuracy: 0.6272, Val Loss: 1.3364, Val Accuracy: 0.5670 Epoch 3189/10000, Train Loss: 1.2888, Train Accuracy: 0.6429, Val Loss: 1.3364, Val Accuracy: 0.5670 Epoch 3190/10000, Train Loss: 1.2940, Train Accuracy: 0.6339, Val Loss: 1.3363, Val Accuracy: 0.5670 Epoch 3191/10000, Train Loss: 1.2930, Train Accuracy: 0.6473, Val Loss: 1.3362, Val Accuracy: 0.5670 Epoch 3192/10000, Train Loss: 1.2877, Train Accuracy: 0.6429, Val Loss: 1.3362, Val Accuracy: 0.5670 Epoch 3193/10000, Train Loss: 1.2914, Train Accuracy: 0.6384, Val Loss: 1.3361, Val Accuracy: 0.5670 Epoch 3194/10000, Train Loss: 1.2872, Train Accuracy: 0.6429, Val Loss: 1.3360, Val Accuracy: 0.5670 Epoch 3195/10000, Train Loss: 1.2988, Train Accuracy: 0.6272, Val Loss: 1.3359, Val Accuracy: 0.5670 Epoch 3196/10000, Train Loss: 1.2912, Train Accuracy: 0.6440, Val Loss: 1.3358, Val Accuracy: 0.5670 Epoch 3197/10000, Train Loss: 1.2941, Train Accuracy: 0.6496, Val Loss: 1.3358, Val Accuracy: 0.5670 Epoch 3198/10000, Train Loss: 1.2841, Train Accuracy: 0.6451, Val Loss: 1.3357, Val Accuracy: 0.5670 Epoch 3199/10000, Train Loss: 1.2934, Train Accuracy: 0.6350, Val Loss: 1.3357, Val Accuracy: 0.5670 Epoch 3200/10000, Train Loss: 1.2973, Train Accuracy: 0.6239, Val Loss: 1.3357, Val Accuracy: 0.5670 Epoch 3201/10000, Train Loss: 1.2877, Train Accuracy: 0.6451, Val Loss: 1.3356, Val Accuracy: 0.5670 Epoch 3202/10000, Train Loss: 1.2848, Train Accuracy: 0.6518, Val Loss: 1.3356, Val Accuracy: 0.5670 Epoch 3203/10000, Train Loss: 1.3017, Train Accuracy: 0.6150, Val Loss: 1.3356, Val Accuracy: 0.5670 Epoch 3204/10000, Train Loss: 1.2885, Train Accuracy: 0.6261, Val Loss: 1.3355, Val Accuracy: 0.5670 Epoch 3205/10000, Train Loss: 1.2813, Train Accuracy: 0.6540, Val Loss: 1.3355, Val Accuracy: 0.5670 Epoch 3206/10000, Train Loss: 1.2918, Train Accuracy: 0.6440, Val Loss: 1.3354, Val Accuracy: 0.5670 Epoch 3207/10000, Train Loss: 1.2873, Train Accuracy: 0.6473, Val Loss: 1.3353, Val Accuracy: 0.5670 Epoch 3208/10000, Train Loss: 1.2936, Train Accuracy: 0.6328, Val Loss: 1.3353, Val Accuracy: 0.5670 Epoch 3209/10000, Train Loss: 1.3001, Train Accuracy: 0.6194, Val Loss: 1.3353, Val Accuracy: 0.5670 Epoch 3210/10000, Train Loss: 1.2931, Train Accuracy: 0.6283, Val Loss: 1.3353, Val Accuracy: 0.5670 Epoch 3211/10000, Train Loss: 1.2863, Train Accuracy: 0.6350, Val Loss: 1.3352, Val Accuracy: 0.5670 Epoch 3212/10000, Train Loss: 1.2888, Train Accuracy: 0.6384, Val Loss: 1.3352, Val Accuracy: 0.5670 Epoch 3213/10000, Train Loss: 1.2909, Train Accuracy: 0.6339, Val Loss: 1.3351, Val Accuracy: 0.5670 Epoch 3214/10000, Train Loss: 1.2781, Train Accuracy: 0.6652, Val Loss: 1.3351, Val Accuracy: 0.5670 Epoch 3215/10000, Train Loss: 1.2845, Train Accuracy: 0.6451, Val Loss: 1.3350, Val Accuracy: 0.5670 Epoch 3216/10000, Train Loss: 1.2898, Train Accuracy: 0.6362, Val Loss: 1.3349, Val Accuracy: 0.5670 Epoch 3217/10000, Train Loss: 1.2825, Train Accuracy: 0.6395, Val Loss: 1.3349, Val Accuracy: 0.5670 Epoch 3218/10000, Train Loss: 1.2958, Train Accuracy: 0.6306, Val Loss: 1.3348, Val Accuracy: 0.5670 Epoch 3219/10000, Train Loss: 1.2943, Train Accuracy: 0.6194, Val Loss: 1.3347, Val Accuracy: 0.5670 Epoch 3220/10000, Train Loss: 1.2901, Train Accuracy: 0.6529, Val Loss: 1.3346, Val Accuracy: 0.5670 Epoch 3221/10000, Train Loss: 1.2918, Train Accuracy: 0.6317, Val Loss: 1.3345, Val Accuracy: 0.5670 Epoch 3222/10000, Train Loss: 1.2788, Train Accuracy: 0.6529, Val Loss: 1.3345, Val Accuracy: 0.5670 Epoch 3223/10000, Train Loss: 1.2916, Train Accuracy: 0.6328, Val Loss: 1.3344, Val Accuracy: 0.5670 Epoch 3224/10000, Train Loss: 1.2914, Train Accuracy: 0.6395, Val Loss: 1.3343, Val Accuracy: 0.5670 Epoch 3225/10000, Train Loss: 1.2968, Train Accuracy: 0.6239, Val Loss: 1.3342, Val Accuracy: 0.5670 Epoch 3226/10000, Train Loss: 1.2849, Train Accuracy: 0.6484, Val Loss: 1.3342, Val Accuracy: 0.5670 Epoch 3227/10000, Train Loss: 1.2864, Train Accuracy: 0.6484, Val Loss: 1.3342, Val Accuracy: 0.5670 Epoch 3228/10000, Train Loss: 1.2854, Train Accuracy: 0.6429, Val Loss: 1.3341, Val Accuracy: 0.5670 Epoch 3229/10000, Train Loss: 1.2904, Train Accuracy: 0.6350, Val Loss: 1.3340, Val Accuracy: 0.5714 Epoch 3230/10000, Train Loss: 1.2950, Train Accuracy: 0.6362, Val Loss: 1.3340, Val Accuracy: 0.5714 Epoch 3231/10000, Train Loss: 1.2889, Train Accuracy: 0.6362, Val Loss: 1.3339, Val Accuracy: 0.5714 Epoch 3232/10000, Train Loss: 1.2903, Train Accuracy: 0.6362, Val Loss: 1.3339, Val Accuracy: 0.5714 Epoch 3233/10000, Train Loss: 1.2892, Train Accuracy: 0.6306, Val Loss: 1.3339, Val Accuracy: 0.5714 Epoch 3234/10000, Train Loss: 1.2846, Train Accuracy: 0.6462, Val Loss: 1.3338, Val Accuracy: 0.5714 Epoch 3235/10000, Train Loss: 1.2811, Train Accuracy: 0.6618, Val Loss: 1.3338, Val Accuracy: 0.5714 Epoch 3236/10000, Train Loss: 1.2903, Train Accuracy: 0.6440, Val Loss: 1.3336, Val Accuracy: 0.5714 Epoch 3237/10000, Train Loss: 1.2856, Train Accuracy: 0.6551, Val Loss: 1.3335, Val Accuracy: 0.5714 Epoch 3238/10000, Train Loss: 1.2907, Train Accuracy: 0.6306, Val Loss: 1.3335, Val Accuracy: 0.5714 Epoch 3239/10000, Train Loss: 1.2902, Train Accuracy: 0.6373, Val Loss: 1.3334, Val Accuracy: 0.5714 Epoch 3240/10000, Train Loss: 1.2777, Train Accuracy: 0.6607, Val Loss: 1.3334, Val Accuracy: 0.5714 Epoch 3241/10000, Train Loss: 1.2730, Train Accuracy: 0.6585, Val Loss: 1.3333, Val Accuracy: 0.5714 Epoch 3242/10000, Train Loss: 1.2911, Train Accuracy: 0.6261, Val Loss: 1.3332, Val Accuracy: 0.5714 Epoch 3243/10000, Train Loss: 1.2894, Train Accuracy: 0.6473, Val Loss: 1.3331, Val Accuracy: 0.5714 Epoch 3244/10000, Train Loss: 1.2921, Train Accuracy: 0.6194, Val Loss: 1.3331, Val Accuracy: 0.5714 Epoch 3245/10000, Train Loss: 1.2933, Train Accuracy: 0.6283, Val Loss: 1.3330, Val Accuracy: 0.5714 Epoch 3246/10000, Train Loss: 1.2907, Train Accuracy: 0.6295, Val Loss: 1.3329, Val Accuracy: 0.5714 Epoch 3247/10000, Train Loss: 1.2858, Train Accuracy: 0.6440, Val Loss: 1.3329, Val Accuracy: 0.5759 Epoch 3248/10000, Train Loss: 1.2930, Train Accuracy: 0.6362, Val Loss: 1.3329, Val Accuracy: 0.5759 Epoch 3249/10000, Train Loss: 1.2874, Train Accuracy: 0.6451, Val Loss: 1.3328, Val Accuracy: 0.5759 Epoch 3250/10000, Train Loss: 1.2846, Train Accuracy: 0.6440, Val Loss: 1.3326, Val Accuracy: 0.5759 Epoch 3251/10000, Train Loss: 1.2791, Train Accuracy: 0.6529, Val Loss: 1.3325, Val Accuracy: 0.5759 Epoch 3252/10000, Train Loss: 1.2881, Train Accuracy: 0.6451, Val Loss: 1.3324, Val Accuracy: 0.5759 Epoch 3253/10000, Train Loss: 1.2887, Train Accuracy: 0.6429, Val Loss: 1.3324, Val Accuracy: 0.5759 Epoch 3254/10000, Train Loss: 1.2857, Train Accuracy: 0.6429, Val Loss: 1.3323, Val Accuracy: 0.5759 Epoch 3255/10000, Train Loss: 1.2936, Train Accuracy: 0.6395, Val Loss: 1.3322, Val Accuracy: 0.5759 Epoch 3256/10000, Train Loss: 1.2880, Train Accuracy: 0.6272, Val Loss: 1.3321, Val Accuracy: 0.5759 Epoch 3257/10000, Train Loss: 1.2798, Train Accuracy: 0.6618, Val Loss: 1.3321, Val Accuracy: 0.5759 Epoch 3258/10000, Train Loss: 1.2740, Train Accuracy: 0.6674, Val Loss: 1.3320, Val Accuracy: 0.5759 Epoch 3259/10000, Train Loss: 1.2687, Train Accuracy: 0.6696, Val Loss: 1.3319, Val Accuracy: 0.5759 Epoch 3260/10000, Train Loss: 1.2871, Train Accuracy: 0.6484, Val Loss: 1.3318, Val Accuracy: 0.5759 Epoch 3261/10000, Train Loss: 1.2805, Train Accuracy: 0.6529, Val Loss: 1.3317, Val Accuracy: 0.5759 Epoch 3262/10000, Train Loss: 1.2799, Train Accuracy: 0.6540, Val Loss: 1.3316, Val Accuracy: 0.5804 Epoch 3263/10000, Train Loss: 1.2856, Train Accuracy: 0.6362, Val Loss: 1.3316, Val Accuracy: 0.5759 Epoch 3264/10000, Train Loss: 1.2899, Train Accuracy: 0.6295, Val Loss: 1.3316, Val Accuracy: 0.5759 Epoch 3265/10000, Train Loss: 1.2887, Train Accuracy: 0.6384, Val Loss: 1.3316, Val Accuracy: 0.5759 Epoch 3266/10000, Train Loss: 1.2900, Train Accuracy: 0.6395, Val Loss: 1.3314, Val Accuracy: 0.5848 Epoch 3267/10000, Train Loss: 1.2723, Train Accuracy: 0.6674, Val Loss: 1.3313, Val Accuracy: 0.5804 Epoch 3268/10000, Train Loss: 1.2855, Train Accuracy: 0.6451, Val Loss: 1.3313, Val Accuracy: 0.5848 Epoch 3269/10000, Train Loss: 1.2793, Train Accuracy: 0.6484, Val Loss: 1.3311, Val Accuracy: 0.5848 Epoch 3270/10000, Train Loss: 1.2846, Train Accuracy: 0.6473, Val Loss: 1.3311, Val Accuracy: 0.5804 Epoch 3271/10000, Train Loss: 1.2728, Train Accuracy: 0.6585, Val Loss: 1.3311, Val Accuracy: 0.5804 Epoch 3272/10000, Train Loss: 1.2733, Train Accuracy: 0.6641, Val Loss: 1.3311, Val Accuracy: 0.5804 Epoch 3273/10000, Train Loss: 1.2771, Train Accuracy: 0.6462, Val Loss: 1.3310, Val Accuracy: 0.5804 Epoch 3274/10000, Train Loss: 1.2922, Train Accuracy: 0.6373, Val Loss: 1.3310, Val Accuracy: 0.5804 Epoch 3275/10000, Train Loss: 1.2732, Train Accuracy: 0.6708, Val Loss: 1.3310, Val Accuracy: 0.5848 Epoch 3276/10000, Train Loss: 1.2776, Train Accuracy: 0.6540, Val Loss: 1.3309, Val Accuracy: 0.5893 Epoch 3277/10000, Train Loss: 1.2792, Train Accuracy: 0.6406, Val Loss: 1.3308, Val Accuracy: 0.5848 Epoch 3278/10000, Train Loss: 1.2791, Train Accuracy: 0.6518, Val Loss: 1.3308, Val Accuracy: 0.5848 Epoch 3279/10000, Train Loss: 1.2633, Train Accuracy: 0.6752, Val Loss: 1.3308, Val Accuracy: 0.5893 Epoch 3280/10000, Train Loss: 1.2774, Train Accuracy: 0.6518, Val Loss: 1.3307, Val Accuracy: 0.5893 Epoch 3281/10000, Train Loss: 1.2816, Train Accuracy: 0.6607, Val Loss: 1.3307, Val Accuracy: 0.5893 Epoch 3282/10000, Train Loss: 1.2793, Train Accuracy: 0.6574, Val Loss: 1.3306, Val Accuracy: 0.5848 Epoch 3283/10000, Train Loss: 1.2792, Train Accuracy: 0.6462, Val Loss: 1.3305, Val Accuracy: 0.5893 Epoch 3284/10000, Train Loss: 1.2704, Train Accuracy: 0.6529, Val Loss: 1.3305, Val Accuracy: 0.5848 Epoch 3285/10000, Train Loss: 1.2758, Train Accuracy: 0.6663, Val Loss: 1.3304, Val Accuracy: 0.5848 Epoch 3286/10000, Train Loss: 1.2770, Train Accuracy: 0.6518, Val Loss: 1.3304, Val Accuracy: 0.5848 Epoch 3287/10000, Train Loss: 1.2775, Train Accuracy: 0.6496, Val Loss: 1.3304, Val Accuracy: 0.5848 Epoch 3288/10000, Train Loss: 1.2948, Train Accuracy: 0.6350, Val Loss: 1.3303, Val Accuracy: 0.5848 Epoch 3289/10000, Train Loss: 1.2764, Train Accuracy: 0.6529, Val Loss: 1.3302, Val Accuracy: 0.5848 Epoch 3290/10000, Train Loss: 1.2704, Train Accuracy: 0.6551, Val Loss: 1.3302, Val Accuracy: 0.5848 Epoch 3291/10000, Train Loss: 1.2881, Train Accuracy: 0.6384, Val Loss: 1.3302, Val Accuracy: 0.5804 Epoch 3292/10000, Train Loss: 1.2744, Train Accuracy: 0.6708, Val Loss: 1.3301, Val Accuracy: 0.5848 Epoch 3293/10000, Train Loss: 1.2849, Train Accuracy: 0.6384, Val Loss: 1.3300, Val Accuracy: 0.5804 Epoch 3294/10000, Train Loss: 1.2768, Train Accuracy: 0.6562, Val Loss: 1.3298, Val Accuracy: 0.5848 Epoch 3295/10000, Train Loss: 1.2772, Train Accuracy: 0.6607, Val Loss: 1.3298, Val Accuracy: 0.5848 Epoch 3296/10000, Train Loss: 1.2846, Train Accuracy: 0.6518, Val Loss: 1.3298, Val Accuracy: 0.5848 Epoch 3297/10000, Train Loss: 1.2905, Train Accuracy: 0.6350, Val Loss: 1.3297, Val Accuracy: 0.5848 Epoch 3298/10000, Train Loss: 1.2704, Train Accuracy: 0.6551, Val Loss: 1.3297, Val Accuracy: 0.5848 Epoch 3299/10000, Train Loss: 1.2825, Train Accuracy: 0.6440, Val Loss: 1.3296, Val Accuracy: 0.5848 Epoch 3300/10000, Train Loss: 1.2827, Train Accuracy: 0.6373, Val Loss: 1.3295, Val Accuracy: 0.5848 Epoch 3301/10000, Train Loss: 1.2903, Train Accuracy: 0.6350, Val Loss: 1.3294, Val Accuracy: 0.5848 Epoch 3302/10000, Train Loss: 1.2662, Train Accuracy: 0.6685, Val Loss: 1.3294, Val Accuracy: 0.5893 Epoch 3303/10000, Train Loss: 1.2840, Train Accuracy: 0.6496, Val Loss: 1.3292, Val Accuracy: 0.5893 Epoch 3304/10000, Train Loss: 1.2827, Train Accuracy: 0.6451, Val Loss: 1.3292, Val Accuracy: 0.5893 Epoch 3305/10000, Train Loss: 1.2863, Train Accuracy: 0.6406, Val Loss: 1.3292, Val Accuracy: 0.5848 Epoch 3306/10000, Train Loss: 1.2693, Train Accuracy: 0.6685, Val Loss: 1.3290, Val Accuracy: 0.5848 Epoch 3307/10000, Train Loss: 1.2728, Train Accuracy: 0.6473, Val Loss: 1.3290, Val Accuracy: 0.5848 Epoch 3308/10000, Train Loss: 1.2850, Train Accuracy: 0.6395, Val Loss: 1.3289, Val Accuracy: 0.5848 Epoch 3309/10000, Train Loss: 1.2855, Train Accuracy: 0.6395, Val Loss: 1.3289, Val Accuracy: 0.5848 Epoch 3310/10000, Train Loss: 1.2785, Train Accuracy: 0.6585, Val Loss: 1.3289, Val Accuracy: 0.5848 Epoch 3311/10000, Train Loss: 1.2820, Train Accuracy: 0.6652, Val Loss: 1.3289, Val Accuracy: 0.5848 Epoch 3312/10000, Train Loss: 1.2876, Train Accuracy: 0.6295, Val Loss: 1.3288, Val Accuracy: 0.5848 Epoch 3313/10000, Train Loss: 1.2804, Train Accuracy: 0.6507, Val Loss: 1.3286, Val Accuracy: 0.5848 Epoch 3314/10000, Train Loss: 1.2762, Train Accuracy: 0.6529, Val Loss: 1.3287, Val Accuracy: 0.5848 Epoch 3315/10000, Train Loss: 1.2759, Train Accuracy: 0.6562, Val Loss: 1.3286, Val Accuracy: 0.5848 Epoch 3316/10000, Train Loss: 1.2824, Train Accuracy: 0.6417, Val Loss: 1.3286, Val Accuracy: 0.5848 Epoch 3317/10000, Train Loss: 1.2854, Train Accuracy: 0.6384, Val Loss: 1.3285, Val Accuracy: 0.5848 Epoch 3318/10000, Train Loss: 1.2807, Train Accuracy: 0.6551, Val Loss: 1.3285, Val Accuracy: 0.5848 Epoch 3319/10000, Train Loss: 1.2698, Train Accuracy: 0.6763, Val Loss: 1.3284, Val Accuracy: 0.5848 Epoch 3320/10000, Train Loss: 1.2747, Train Accuracy: 0.6618, Val Loss: 1.3284, Val Accuracy: 0.5848 Epoch 3321/10000, Train Loss: 1.2833, Train Accuracy: 0.6373, Val Loss: 1.3284, Val Accuracy: 0.5848 Epoch 3322/10000, Train Loss: 1.2783, Train Accuracy: 0.6406, Val Loss: 1.3283, Val Accuracy: 0.5848 Epoch 3323/10000, Train Loss: 1.2864, Train Accuracy: 0.6306, Val Loss: 1.3282, Val Accuracy: 0.5848 Epoch 3324/10000, Train Loss: 1.2656, Train Accuracy: 0.6730, Val Loss: 1.3282, Val Accuracy: 0.5848 Epoch 3325/10000, Train Loss: 1.2744, Train Accuracy: 0.6551, Val Loss: 1.3283, Val Accuracy: 0.5848 Epoch 3326/10000, Train Loss: 1.2852, Train Accuracy: 0.6384, Val Loss: 1.3282, Val Accuracy: 0.5893 Epoch 3327/10000, Train Loss: 1.2763, Train Accuracy: 0.6417, Val Loss: 1.3282, Val Accuracy: 0.5848 Epoch 3328/10000, Train Loss: 1.2776, Train Accuracy: 0.6507, Val Loss: 1.3282, Val Accuracy: 0.5848 Epoch 3329/10000, Train Loss: 1.2682, Train Accuracy: 0.6629, Val Loss: 1.3281, Val Accuracy: 0.5848 Epoch 3330/10000, Train Loss: 1.2720, Train Accuracy: 0.6529, Val Loss: 1.3279, Val Accuracy: 0.5848 Epoch 3331/10000, Train Loss: 1.2806, Train Accuracy: 0.6451, Val Loss: 1.3278, Val Accuracy: 0.5848 Epoch 3332/10000, Train Loss: 1.2685, Train Accuracy: 0.6674, Val Loss: 1.3277, Val Accuracy: 0.5848 Epoch 3333/10000, Train Loss: 1.2815, Train Accuracy: 0.6440, Val Loss: 1.3276, Val Accuracy: 0.5848 Epoch 3334/10000, Train Loss: 1.2722, Train Accuracy: 0.6585, Val Loss: 1.3275, Val Accuracy: 0.5848 Epoch 3335/10000, Train Loss: 1.2711, Train Accuracy: 0.6529, Val Loss: 1.3274, Val Accuracy: 0.5848 Epoch 3336/10000, Train Loss: 1.2764, Train Accuracy: 0.6607, Val Loss: 1.3274, Val Accuracy: 0.5848 Epoch 3337/10000, Train Loss: 1.2759, Train Accuracy: 0.6585, Val Loss: 1.3273, Val Accuracy: 0.5804 Epoch 3338/10000, Train Loss: 1.2656, Train Accuracy: 0.6574, Val Loss: 1.3273, Val Accuracy: 0.5848 Epoch 3339/10000, Train Loss: 1.2781, Train Accuracy: 0.6484, Val Loss: 1.3272, Val Accuracy: 0.5848 Epoch 3340/10000, Train Loss: 1.2801, Train Accuracy: 0.6373, Val Loss: 1.3272, Val Accuracy: 0.5848 Epoch 3341/10000, Train Loss: 1.2787, Train Accuracy: 0.6484, Val Loss: 1.3272, Val Accuracy: 0.5848 Epoch 3342/10000, Train Loss: 1.2737, Train Accuracy: 0.6585, Val Loss: 1.3271, Val Accuracy: 0.5848 Epoch 3343/10000, Train Loss: 1.2862, Train Accuracy: 0.6406, Val Loss: 1.3270, Val Accuracy: 0.5893 Epoch 3344/10000, Train Loss: 1.2795, Train Accuracy: 0.6585, Val Loss: 1.3270, Val Accuracy: 0.5893 Epoch 3345/10000, Train Loss: 1.2779, Train Accuracy: 0.6473, Val Loss: 1.3270, Val Accuracy: 0.5893 Epoch 3346/10000, Train Loss: 1.2734, Train Accuracy: 0.6507, Val Loss: 1.3269, Val Accuracy: 0.5848 Epoch 3347/10000, Train Loss: 1.2842, Train Accuracy: 0.6473, Val Loss: 1.3269, Val Accuracy: 0.5848 Epoch 3348/10000, Train Loss: 1.2671, Train Accuracy: 0.6674, Val Loss: 1.3269, Val Accuracy: 0.5893 Epoch 3349/10000, Train Loss: 1.2661, Train Accuracy: 0.6696, Val Loss: 1.3267, Val Accuracy: 0.5893 Epoch 3350/10000, Train Loss: 1.2771, Train Accuracy: 0.6462, Val Loss: 1.3268, Val Accuracy: 0.5893 Epoch 3351/10000, Train Loss: 1.2641, Train Accuracy: 0.6763, Val Loss: 1.3267, Val Accuracy: 0.5893 Epoch 3352/10000, Train Loss: 1.2863, Train Accuracy: 0.6429, Val Loss: 1.3267, Val Accuracy: 0.5893 Epoch 3353/10000, Train Loss: 1.2699, Train Accuracy: 0.6674, Val Loss: 1.3267, Val Accuracy: 0.5893 Epoch 3354/10000, Train Loss: 1.2811, Train Accuracy: 0.6417, Val Loss: 1.3266, Val Accuracy: 0.5938 Epoch 3355/10000, Train Loss: 1.2689, Train Accuracy: 0.6629, Val Loss: 1.3266, Val Accuracy: 0.5893 Epoch 3356/10000, Train Loss: 1.2801, Train Accuracy: 0.6507, Val Loss: 1.3265, Val Accuracy: 0.5893 Epoch 3357/10000, Train Loss: 1.2748, Train Accuracy: 0.6473, Val Loss: 1.3264, Val Accuracy: 0.5893 Epoch 3358/10000, Train Loss: 1.2716, Train Accuracy: 0.6462, Val Loss: 1.3264, Val Accuracy: 0.5893 Epoch 3359/10000, Train Loss: 1.2714, Train Accuracy: 0.6596, Val Loss: 1.3263, Val Accuracy: 0.5893 Epoch 3360/10000, Train Loss: 1.2686, Train Accuracy: 0.6741, Val Loss: 1.3262, Val Accuracy: 0.5893 Epoch 3361/10000, Train Loss: 1.2762, Train Accuracy: 0.6484, Val Loss: 1.3262, Val Accuracy: 0.5893 Epoch 3362/10000, Train Loss: 1.2577, Train Accuracy: 0.6674, Val Loss: 1.3262, Val Accuracy: 0.5893 Epoch 3363/10000, Train Loss: 1.2784, Train Accuracy: 0.6529, Val Loss: 1.3261, Val Accuracy: 0.5893 Epoch 3364/10000, Train Loss: 1.2835, Train Accuracy: 0.6451, Val Loss: 1.3260, Val Accuracy: 0.5893 Epoch 3365/10000, Train Loss: 1.2684, Train Accuracy: 0.6496, Val Loss: 1.3259, Val Accuracy: 0.5893 Epoch 3366/10000, Train Loss: 1.2714, Train Accuracy: 0.6696, Val Loss: 1.3258, Val Accuracy: 0.5893 Epoch 3367/10000, Train Loss: 1.2707, Train Accuracy: 0.6551, Val Loss: 1.3257, Val Accuracy: 0.5893 Epoch 3368/10000, Train Loss: 1.2632, Train Accuracy: 0.6629, Val Loss: 1.3257, Val Accuracy: 0.5893 Epoch 3369/10000, Train Loss: 1.2708, Train Accuracy: 0.6484, Val Loss: 1.3257, Val Accuracy: 0.5893 Epoch 3370/10000, Train Loss: 1.2729, Train Accuracy: 0.6585, Val Loss: 1.3256, Val Accuracy: 0.5893 Epoch 3371/10000, Train Loss: 1.2727, Train Accuracy: 0.6596, Val Loss: 1.3256, Val Accuracy: 0.5893 Epoch 3372/10000, Train Loss: 1.2853, Train Accuracy: 0.6362, Val Loss: 1.3255, Val Accuracy: 0.5893 Epoch 3373/10000, Train Loss: 1.2677, Train Accuracy: 0.6518, Val Loss: 1.3254, Val Accuracy: 0.5893 Epoch 3374/10000, Train Loss: 1.2787, Train Accuracy: 0.6618, Val Loss: 1.3253, Val Accuracy: 0.5893 Epoch 3375/10000, Train Loss: 1.2699, Train Accuracy: 0.6641, Val Loss: 1.3253, Val Accuracy: 0.5893 Epoch 3376/10000, Train Loss: 1.2735, Train Accuracy: 0.6518, Val Loss: 1.3252, Val Accuracy: 0.5893 Epoch 3377/10000, Train Loss: 1.2766, Train Accuracy: 0.6440, Val Loss: 1.3252, Val Accuracy: 0.5893 Epoch 3378/10000, Train Loss: 1.2871, Train Accuracy: 0.6395, Val Loss: 1.3251, Val Accuracy: 0.5893 Epoch 3379/10000, Train Loss: 1.2726, Train Accuracy: 0.6518, Val Loss: 1.3250, Val Accuracy: 0.5893 Epoch 3380/10000, Train Loss: 1.2649, Train Accuracy: 0.6629, Val Loss: 1.3250, Val Accuracy: 0.5893 Epoch 3381/10000, Train Loss: 1.2718, Train Accuracy: 0.6596, Val Loss: 1.3249, Val Accuracy: 0.5848 Epoch 3382/10000, Train Loss: 1.2674, Train Accuracy: 0.6641, Val Loss: 1.3248, Val Accuracy: 0.5893 Epoch 3383/10000, Train Loss: 1.2729, Train Accuracy: 0.6496, Val Loss: 1.3247, Val Accuracy: 0.5893 Epoch 3384/10000, Train Loss: 1.2812, Train Accuracy: 0.6373, Val Loss: 1.3247, Val Accuracy: 0.5893 Epoch 3385/10000, Train Loss: 1.2675, Train Accuracy: 0.6663, Val Loss: 1.3246, Val Accuracy: 0.5893 Epoch 3386/10000, Train Loss: 1.2710, Train Accuracy: 0.6674, Val Loss: 1.3245, Val Accuracy: 0.5848 Epoch 3387/10000, Train Loss: 1.2777, Train Accuracy: 0.6540, Val Loss: 1.3244, Val Accuracy: 0.5848 Epoch 3388/10000, Train Loss: 1.2636, Train Accuracy: 0.6618, Val Loss: 1.3245, Val Accuracy: 0.5848 Epoch 3389/10000, Train Loss: 1.2738, Train Accuracy: 0.6429, Val Loss: 1.3244, Val Accuracy: 0.5848 Epoch 3390/10000, Train Loss: 1.2713, Train Accuracy: 0.6641, Val Loss: 1.3243, Val Accuracy: 0.5848 Epoch 3391/10000, Train Loss: 1.2826, Train Accuracy: 0.6350, Val Loss: 1.3242, Val Accuracy: 0.5848 Epoch 3392/10000, Train Loss: 1.2744, Train Accuracy: 0.6395, Val Loss: 1.3242, Val Accuracy: 0.5848 Epoch 3393/10000, Train Loss: 1.2715, Train Accuracy: 0.6551, Val Loss: 1.3241, Val Accuracy: 0.5848 Epoch 3394/10000, Train Loss: 1.2637, Train Accuracy: 0.6741, Val Loss: 1.3240, Val Accuracy: 0.5848 Epoch 3395/10000, Train Loss: 1.2665, Train Accuracy: 0.6652, Val Loss: 1.3239, Val Accuracy: 0.5848 Epoch 3396/10000, Train Loss: 1.2728, Train Accuracy: 0.6417, Val Loss: 1.3239, Val Accuracy: 0.5848 Epoch 3397/10000, Train Loss: 1.2719, Train Accuracy: 0.6585, Val Loss: 1.3238, Val Accuracy: 0.5848 Epoch 3398/10000, Train Loss: 1.2718, Train Accuracy: 0.6462, Val Loss: 1.3238, Val Accuracy: 0.5848 Epoch 3399/10000, Train Loss: 1.2597, Train Accuracy: 0.6585, Val Loss: 1.3238, Val Accuracy: 0.5848 Epoch 3400/10000, Train Loss: 1.2748, Train Accuracy: 0.6629, Val Loss: 1.3238, Val Accuracy: 0.5848 Epoch 3401/10000, Train Loss: 1.2682, Train Accuracy: 0.6685, Val Loss: 1.3237, Val Accuracy: 0.5848 Epoch 3402/10000, Train Loss: 1.2666, Train Accuracy: 0.6607, Val Loss: 1.3236, Val Accuracy: 0.5848 Epoch 3403/10000, Train Loss: 1.2731, Train Accuracy: 0.6652, Val Loss: 1.3236, Val Accuracy: 0.5848 Epoch 3404/10000, Train Loss: 1.2633, Train Accuracy: 0.6763, Val Loss: 1.3236, Val Accuracy: 0.5848 Epoch 3405/10000, Train Loss: 1.2644, Train Accuracy: 0.6596, Val Loss: 1.3235, Val Accuracy: 0.5848 Epoch 3406/10000, Train Loss: 1.2686, Train Accuracy: 0.6629, Val Loss: 1.3235, Val Accuracy: 0.5848 Epoch 3407/10000, Train Loss: 1.2640, Train Accuracy: 0.6663, Val Loss: 1.3234, Val Accuracy: 0.5848 Epoch 3408/10000, Train Loss: 1.2628, Train Accuracy: 0.6708, Val Loss: 1.3235, Val Accuracy: 0.5848 Epoch 3409/10000, Train Loss: 1.2711, Train Accuracy: 0.6518, Val Loss: 1.3233, Val Accuracy: 0.5848 Epoch 3410/10000, Train Loss: 1.2719, Train Accuracy: 0.6540, Val Loss: 1.3233, Val Accuracy: 0.5848 Epoch 3411/10000, Train Loss: 1.2695, Train Accuracy: 0.6652, Val Loss: 1.3234, Val Accuracy: 0.5848 Epoch 3412/10000, Train Loss: 1.2635, Train Accuracy: 0.6641, Val Loss: 1.3233, Val Accuracy: 0.5848 Epoch 3413/10000, Train Loss: 1.2749, Train Accuracy: 0.6641, Val Loss: 1.3233, Val Accuracy: 0.5848 Epoch 3414/10000, Train Loss: 1.2703, Train Accuracy: 0.6540, Val Loss: 1.3232, Val Accuracy: 0.5848 Epoch 3415/10000, Train Loss: 1.2655, Train Accuracy: 0.6574, Val Loss: 1.3231, Val Accuracy: 0.5848 Epoch 3416/10000, Train Loss: 1.2749, Train Accuracy: 0.6507, Val Loss: 1.3230, Val Accuracy: 0.5848 Epoch 3417/10000, Train Loss: 1.2666, Train Accuracy: 0.6540, Val Loss: 1.3230, Val Accuracy: 0.5848 Epoch 3418/10000, Train Loss: 1.2656, Train Accuracy: 0.6529, Val Loss: 1.3229, Val Accuracy: 0.5848 Epoch 3419/10000, Train Loss: 1.2759, Train Accuracy: 0.6440, Val Loss: 1.3229, Val Accuracy: 0.5848 Epoch 3420/10000, Train Loss: 1.2700, Train Accuracy: 0.6585, Val Loss: 1.3228, Val Accuracy: 0.5848 Epoch 3421/10000, Train Loss: 1.2767, Train Accuracy: 0.6451, Val Loss: 1.3227, Val Accuracy: 0.5848 Epoch 3422/10000, Train Loss: 1.2806, Train Accuracy: 0.6328, Val Loss: 1.3227, Val Accuracy: 0.5848 Epoch 3423/10000, Train Loss: 1.2618, Train Accuracy: 0.6696, Val Loss: 1.3226, Val Accuracy: 0.5848 Epoch 3424/10000, Train Loss: 1.2679, Train Accuracy: 0.6674, Val Loss: 1.3226, Val Accuracy: 0.5848 Epoch 3425/10000, Train Loss: 1.2739, Train Accuracy: 0.6596, Val Loss: 1.3225, Val Accuracy: 0.5848 Epoch 3426/10000, Train Loss: 1.2717, Train Accuracy: 0.6596, Val Loss: 1.3225, Val Accuracy: 0.5848 Epoch 3427/10000, Train Loss: 1.2653, Train Accuracy: 0.6641, Val Loss: 1.3224, Val Accuracy: 0.5848 Epoch 3428/10000, Train Loss: 1.2601, Train Accuracy: 0.6652, Val Loss: 1.3223, Val Accuracy: 0.5848 Epoch 3429/10000, Train Loss: 1.2722, Train Accuracy: 0.6496, Val Loss: 1.3224, Val Accuracy: 0.5848 Epoch 3430/10000, Train Loss: 1.2698, Train Accuracy: 0.6618, Val Loss: 1.3222, Val Accuracy: 0.5848 Epoch 3431/10000, Train Loss: 1.2753, Train Accuracy: 0.6562, Val Loss: 1.3222, Val Accuracy: 0.5848 Epoch 3432/10000, Train Loss: 1.2724, Train Accuracy: 0.6484, Val Loss: 1.3221, Val Accuracy: 0.5848 Epoch 3433/10000, Train Loss: 1.2732, Train Accuracy: 0.6417, Val Loss: 1.3221, Val Accuracy: 0.5848 Epoch 3434/10000, Train Loss: 1.2728, Train Accuracy: 0.6596, Val Loss: 1.3220, Val Accuracy: 0.5848 Epoch 3435/10000, Train Loss: 1.2609, Train Accuracy: 0.6786, Val Loss: 1.3221, Val Accuracy: 0.5848 Epoch 3436/10000, Train Loss: 1.2657, Train Accuracy: 0.6685, Val Loss: 1.3220, Val Accuracy: 0.5848 Epoch 3437/10000, Train Loss: 1.2660, Train Accuracy: 0.6741, Val Loss: 1.3220, Val Accuracy: 0.5848 Epoch 3438/10000, Train Loss: 1.2760, Train Accuracy: 0.6462, Val Loss: 1.3219, Val Accuracy: 0.5848 Epoch 3439/10000, Train Loss: 1.2600, Train Accuracy: 0.6685, Val Loss: 1.3219, Val Accuracy: 0.5848 Epoch 3440/10000, Train Loss: 1.2618, Train Accuracy: 0.6663, Val Loss: 1.3218, Val Accuracy: 0.5848 Epoch 3441/10000, Train Loss: 1.2743, Train Accuracy: 0.6429, Val Loss: 1.3218, Val Accuracy: 0.5848 Epoch 3442/10000, Train Loss: 1.2669, Train Accuracy: 0.6652, Val Loss: 1.3217, Val Accuracy: 0.5848 Epoch 3443/10000, Train Loss: 1.2682, Train Accuracy: 0.6663, Val Loss: 1.3217, Val Accuracy: 0.5848 Epoch 3444/10000, Train Loss: 1.2646, Train Accuracy: 0.6641, Val Loss: 1.3216, Val Accuracy: 0.5848 Epoch 3445/10000, Train Loss: 1.2781, Train Accuracy: 0.6339, Val Loss: 1.3216, Val Accuracy: 0.5848 Epoch 3446/10000, Train Loss: 1.2659, Train Accuracy: 0.6596, Val Loss: 1.3215, Val Accuracy: 0.5848 Epoch 3447/10000, Train Loss: 1.2626, Train Accuracy: 0.6641, Val Loss: 1.3215, Val Accuracy: 0.5848 Epoch 3448/10000, Train Loss: 1.2522, Train Accuracy: 0.6708, Val Loss: 1.3214, Val Accuracy: 0.5848 Epoch 3449/10000, Train Loss: 1.2615, Train Accuracy: 0.6562, Val Loss: 1.3214, Val Accuracy: 0.5848 Epoch 3450/10000, Train Loss: 1.2708, Train Accuracy: 0.6629, Val Loss: 1.3214, Val Accuracy: 0.5848 Epoch 3451/10000, Train Loss: 1.2663, Train Accuracy: 0.6596, Val Loss: 1.3213, Val Accuracy: 0.5848 Epoch 3452/10000, Train Loss: 1.2622, Train Accuracy: 0.6663, Val Loss: 1.3212, Val Accuracy: 0.5848 Epoch 3453/10000, Train Loss: 1.2478, Train Accuracy: 0.6842, Val Loss: 1.3211, Val Accuracy: 0.5848 Epoch 3454/10000, Train Loss: 1.2605, Train Accuracy: 0.6652, Val Loss: 1.3212, Val Accuracy: 0.5848 Epoch 3455/10000, Train Loss: 1.2652, Train Accuracy: 0.6607, Val Loss: 1.3210, Val Accuracy: 0.5848 Epoch 3456/10000, Train Loss: 1.2565, Train Accuracy: 0.6819, Val Loss: 1.3211, Val Accuracy: 0.5848 Epoch 3457/10000, Train Loss: 1.2676, Train Accuracy: 0.6540, Val Loss: 1.3209, Val Accuracy: 0.5848 Epoch 3458/10000, Train Loss: 1.2615, Train Accuracy: 0.6596, Val Loss: 1.3208, Val Accuracy: 0.5848 Epoch 3459/10000, Train Loss: 1.2625, Train Accuracy: 0.6652, Val Loss: 1.3208, Val Accuracy: 0.5848 Epoch 3460/10000, Train Loss: 1.2675, Train Accuracy: 0.6451, Val Loss: 1.3206, Val Accuracy: 0.5848 Epoch 3461/10000, Train Loss: 1.2661, Train Accuracy: 0.6618, Val Loss: 1.3206, Val Accuracy: 0.5848 Epoch 3462/10000, Train Loss: 1.2590, Train Accuracy: 0.6518, Val Loss: 1.3205, Val Accuracy: 0.5848 Epoch 3463/10000, Train Loss: 1.2623, Train Accuracy: 0.6674, Val Loss: 1.3205, Val Accuracy: 0.5848 Epoch 3464/10000, Train Loss: 1.2641, Train Accuracy: 0.6730, Val Loss: 1.3204, Val Accuracy: 0.5848 Epoch 3465/10000, Train Loss: 1.2686, Train Accuracy: 0.6618, Val Loss: 1.3204, Val Accuracy: 0.5848 Epoch 3466/10000, Train Loss: 1.2671, Train Accuracy: 0.6641, Val Loss: 1.3203, Val Accuracy: 0.5848 Epoch 3467/10000, Train Loss: 1.2682, Train Accuracy: 0.6607, Val Loss: 1.3203, Val Accuracy: 0.5848 Epoch 3468/10000, Train Loss: 1.2607, Train Accuracy: 0.6629, Val Loss: 1.3202, Val Accuracy: 0.5848 Epoch 3469/10000, Train Loss: 1.2701, Train Accuracy: 0.6551, Val Loss: 1.3200, Val Accuracy: 0.5848 Epoch 3470/10000, Train Loss: 1.2581, Train Accuracy: 0.6730, Val Loss: 1.3200, Val Accuracy: 0.5848 Epoch 3471/10000, Train Loss: 1.2661, Train Accuracy: 0.6663, Val Loss: 1.3200, Val Accuracy: 0.5848 Epoch 3472/10000, Train Loss: 1.2655, Train Accuracy: 0.6763, Val Loss: 1.3200, Val Accuracy: 0.5848 Epoch 3473/10000, Train Loss: 1.2631, Train Accuracy: 0.6607, Val Loss: 1.3198, Val Accuracy: 0.5848 Epoch 3474/10000, Train Loss: 1.2684, Train Accuracy: 0.6607, Val Loss: 1.3197, Val Accuracy: 0.5848 Epoch 3475/10000, Train Loss: 1.2746, Train Accuracy: 0.6429, Val Loss: 1.3197, Val Accuracy: 0.5848 Epoch 3476/10000, Train Loss: 1.2680, Train Accuracy: 0.6529, Val Loss: 1.3196, Val Accuracy: 0.5848 Epoch 3477/10000, Train Loss: 1.2707, Train Accuracy: 0.6518, Val Loss: 1.3196, Val Accuracy: 0.5848 Epoch 3478/10000, Train Loss: 1.2743, Train Accuracy: 0.6518, Val Loss: 1.3195, Val Accuracy: 0.5848 Epoch 3479/10000, Train Loss: 1.2590, Train Accuracy: 0.6708, Val Loss: 1.3195, Val Accuracy: 0.5848 Epoch 3480/10000, Train Loss: 1.2542, Train Accuracy: 0.6808, Val Loss: 1.3194, Val Accuracy: 0.5848 Epoch 3481/10000, Train Loss: 1.2605, Train Accuracy: 0.6696, Val Loss: 1.3193, Val Accuracy: 0.5848 Epoch 3482/10000, Train Loss: 1.2560, Train Accuracy: 0.6708, Val Loss: 1.3193, Val Accuracy: 0.5848 Epoch 3483/10000, Train Loss: 1.2654, Train Accuracy: 0.6652, Val Loss: 1.3192, Val Accuracy: 0.5848 Epoch 3484/10000, Train Loss: 1.2599, Train Accuracy: 0.6685, Val Loss: 1.3191, Val Accuracy: 0.5848 Epoch 3485/10000, Train Loss: 1.2597, Train Accuracy: 0.6596, Val Loss: 1.3190, Val Accuracy: 0.5848 Epoch 3486/10000, Train Loss: 1.2698, Train Accuracy: 0.6585, Val Loss: 1.3190, Val Accuracy: 0.5848 Epoch 3487/10000, Train Loss: 1.2624, Train Accuracy: 0.6596, Val Loss: 1.3189, Val Accuracy: 0.5848 Epoch 3488/10000, Train Loss: 1.2529, Train Accuracy: 0.6797, Val Loss: 1.3189, Val Accuracy: 0.5848 Epoch 3489/10000, Train Loss: 1.2655, Train Accuracy: 0.6473, Val Loss: 1.3189, Val Accuracy: 0.5848 Epoch 3490/10000, Train Loss: 1.2608, Train Accuracy: 0.6685, Val Loss: 1.3189, Val Accuracy: 0.5848 Epoch 3491/10000, Train Loss: 1.2558, Train Accuracy: 0.6842, Val Loss: 1.3188, Val Accuracy: 0.5848 Epoch 3492/10000, Train Loss: 1.2603, Train Accuracy: 0.6674, Val Loss: 1.3188, Val Accuracy: 0.5848 Epoch 3493/10000, Train Loss: 1.2731, Train Accuracy: 0.6518, Val Loss: 1.3187, Val Accuracy: 0.5848 Epoch 3494/10000, Train Loss: 1.2698, Train Accuracy: 0.6373, Val Loss: 1.3187, Val Accuracy: 0.5848 Epoch 3495/10000, Train Loss: 1.2723, Train Accuracy: 0.6484, Val Loss: 1.3186, Val Accuracy: 0.5848 Epoch 3496/10000, Train Loss: 1.2630, Train Accuracy: 0.6708, Val Loss: 1.3185, Val Accuracy: 0.5848 Epoch 3497/10000, Train Loss: 1.2566, Train Accuracy: 0.6719, Val Loss: 1.3184, Val Accuracy: 0.5848 Epoch 3498/10000, Train Loss: 1.2541, Train Accuracy: 0.6786, Val Loss: 1.3184, Val Accuracy: 0.5848 Epoch 3499/10000, Train Loss: 1.2533, Train Accuracy: 0.6730, Val Loss: 1.3184, Val Accuracy: 0.5848 Epoch 3500/10000, Train Loss: 1.2619, Train Accuracy: 0.6685, Val Loss: 1.3183, Val Accuracy: 0.5848 Epoch 3501/10000, Train Loss: 1.2485, Train Accuracy: 0.6886, Val Loss: 1.3183, Val Accuracy: 0.5848 Epoch 3502/10000, Train Loss: 1.2580, Train Accuracy: 0.6719, Val Loss: 1.3182, Val Accuracy: 0.5848 Epoch 3503/10000, Train Loss: 1.2670, Train Accuracy: 0.6641, Val Loss: 1.3181, Val Accuracy: 0.5848 Epoch 3504/10000, Train Loss: 1.2647, Train Accuracy: 0.6585, Val Loss: 1.3181, Val Accuracy: 0.5804 Epoch 3505/10000, Train Loss: 1.2645, Train Accuracy: 0.6607, Val Loss: 1.3181, Val Accuracy: 0.5804 Epoch 3506/10000, Train Loss: 1.2612, Train Accuracy: 0.6618, Val Loss: 1.3179, Val Accuracy: 0.5848 Epoch 3507/10000, Train Loss: 1.2673, Train Accuracy: 0.6618, Val Loss: 1.3178, Val Accuracy: 0.5848 Epoch 3508/10000, Train Loss: 1.2543, Train Accuracy: 0.6819, Val Loss: 1.3177, Val Accuracy: 0.5848 Epoch 3509/10000, Train Loss: 1.2571, Train Accuracy: 0.6663, Val Loss: 1.3177, Val Accuracy: 0.5848 Epoch 3510/10000, Train Loss: 1.2629, Train Accuracy: 0.6618, Val Loss: 1.3176, Val Accuracy: 0.5848 Epoch 3511/10000, Train Loss: 1.2687, Train Accuracy: 0.6507, Val Loss: 1.3176, Val Accuracy: 0.5804 Epoch 3512/10000, Train Loss: 1.2726, Train Accuracy: 0.6496, Val Loss: 1.3176, Val Accuracy: 0.5804 Epoch 3513/10000, Train Loss: 1.2474, Train Accuracy: 0.6886, Val Loss: 1.3176, Val Accuracy: 0.5804 Epoch 3514/10000, Train Loss: 1.2568, Train Accuracy: 0.6708, Val Loss: 1.3175, Val Accuracy: 0.5804 Epoch 3515/10000, Train Loss: 1.2630, Train Accuracy: 0.6618, Val Loss: 1.3174, Val Accuracy: 0.5848 Epoch 3516/10000, Train Loss: 1.2656, Train Accuracy: 0.6529, Val Loss: 1.3173, Val Accuracy: 0.5848 Epoch 3517/10000, Train Loss: 1.2615, Train Accuracy: 0.6551, Val Loss: 1.3172, Val Accuracy: 0.5804 Epoch 3518/10000, Train Loss: 1.2616, Train Accuracy: 0.6641, Val Loss: 1.3171, Val Accuracy: 0.5848 Epoch 3519/10000, Train Loss: 1.2589, Train Accuracy: 0.6629, Val Loss: 1.3170, Val Accuracy: 0.5804 Epoch 3520/10000, Train Loss: 1.2529, Train Accuracy: 0.6819, Val Loss: 1.3170, Val Accuracy: 0.5804 Epoch 3521/10000, Train Loss: 1.2574, Train Accuracy: 0.6629, Val Loss: 1.3169, Val Accuracy: 0.5848 Epoch 3522/10000, Train Loss: 1.2509, Train Accuracy: 0.6663, Val Loss: 1.3169, Val Accuracy: 0.5848 Epoch 3523/10000, Train Loss: 1.2564, Train Accuracy: 0.6663, Val Loss: 1.3169, Val Accuracy: 0.5848 Epoch 3524/10000, Train Loss: 1.2589, Train Accuracy: 0.6641, Val Loss: 1.3169, Val Accuracy: 0.5804 Epoch 3525/10000, Train Loss: 1.2559, Train Accuracy: 0.6641, Val Loss: 1.3169, Val Accuracy: 0.5804 Epoch 3526/10000, Train Loss: 1.2648, Train Accuracy: 0.6674, Val Loss: 1.3167, Val Accuracy: 0.5848 Epoch 3527/10000, Train Loss: 1.2577, Train Accuracy: 0.6652, Val Loss: 1.3167, Val Accuracy: 0.5848 Epoch 3528/10000, Train Loss: 1.2600, Train Accuracy: 0.6618, Val Loss: 1.3167, Val Accuracy: 0.5848 Epoch 3529/10000, Train Loss: 1.2590, Train Accuracy: 0.6551, Val Loss: 1.3167, Val Accuracy: 0.5848 Epoch 3530/10000, Train Loss: 1.2646, Train Accuracy: 0.6585, Val Loss: 1.3167, Val Accuracy: 0.5848 Epoch 3531/10000, Train Loss: 1.2520, Train Accuracy: 0.6708, Val Loss: 1.3166, Val Accuracy: 0.5848 Epoch 3532/10000, Train Loss: 1.2617, Train Accuracy: 0.6719, Val Loss: 1.3166, Val Accuracy: 0.5848 Epoch 3533/10000, Train Loss: 1.2500, Train Accuracy: 0.6775, Val Loss: 1.3165, Val Accuracy: 0.5848 Epoch 3534/10000, Train Loss: 1.2594, Train Accuracy: 0.6652, Val Loss: 1.3165, Val Accuracy: 0.5848 Epoch 3535/10000, Train Loss: 1.2537, Train Accuracy: 0.6775, Val Loss: 1.3164, Val Accuracy: 0.5848 Epoch 3536/10000, Train Loss: 1.2587, Train Accuracy: 0.6708, Val Loss: 1.3164, Val Accuracy: 0.5893 Epoch 3537/10000, Train Loss: 1.2677, Train Accuracy: 0.6585, Val Loss: 1.3163, Val Accuracy: 0.5848 Epoch 3538/10000, Train Loss: 1.2565, Train Accuracy: 0.6685, Val Loss: 1.3162, Val Accuracy: 0.5848 Epoch 3539/10000, Train Loss: 1.2610, Train Accuracy: 0.6696, Val Loss: 1.3161, Val Accuracy: 0.5848 Epoch 3540/10000, Train Loss: 1.2597, Train Accuracy: 0.6685, Val Loss: 1.3160, Val Accuracy: 0.5848 Epoch 3541/10000, Train Loss: 1.2638, Train Accuracy: 0.6618, Val Loss: 1.3159, Val Accuracy: 0.5893 Epoch 3542/10000, Train Loss: 1.2616, Train Accuracy: 0.6685, Val Loss: 1.3159, Val Accuracy: 0.5893 Epoch 3543/10000, Train Loss: 1.2594, Train Accuracy: 0.6629, Val Loss: 1.3158, Val Accuracy: 0.5938 Epoch 3544/10000, Train Loss: 1.2683, Train Accuracy: 0.6685, Val Loss: 1.3158, Val Accuracy: 0.5893 Epoch 3545/10000, Train Loss: 1.2572, Train Accuracy: 0.6696, Val Loss: 1.3157, Val Accuracy: 0.5893 Epoch 3546/10000, Train Loss: 1.2643, Train Accuracy: 0.6607, Val Loss: 1.3156, Val Accuracy: 0.5893 Epoch 3547/10000, Train Loss: 1.2535, Train Accuracy: 0.6685, Val Loss: 1.3156, Val Accuracy: 0.5893 Epoch 3548/10000, Train Loss: 1.2561, Train Accuracy: 0.6763, Val Loss: 1.3156, Val Accuracy: 0.5893 Epoch 3549/10000, Train Loss: 1.2644, Train Accuracy: 0.6618, Val Loss: 1.3156, Val Accuracy: 0.5893 Epoch 3550/10000, Train Loss: 1.2587, Train Accuracy: 0.6696, Val Loss: 1.3156, Val Accuracy: 0.5893 Epoch 3551/10000, Train Loss: 1.2489, Train Accuracy: 0.6808, Val Loss: 1.3156, Val Accuracy: 0.5893 Epoch 3552/10000, Train Loss: 1.2535, Train Accuracy: 0.6719, Val Loss: 1.3155, Val Accuracy: 0.5893 Epoch 3553/10000, Train Loss: 1.2635, Train Accuracy: 0.6540, Val Loss: 1.3155, Val Accuracy: 0.5893 Epoch 3554/10000, Train Loss: 1.2479, Train Accuracy: 0.6842, Val Loss: 1.3155, Val Accuracy: 0.5893 Epoch 3555/10000, Train Loss: 1.2469, Train Accuracy: 0.6864, Val Loss: 1.3153, Val Accuracy: 0.5893 Epoch 3556/10000, Train Loss: 1.2578, Train Accuracy: 0.6708, Val Loss: 1.3153, Val Accuracy: 0.5893 Epoch 3557/10000, Train Loss: 1.2503, Train Accuracy: 0.6797, Val Loss: 1.3154, Val Accuracy: 0.5893 Epoch 3558/10000, Train Loss: 1.2602, Train Accuracy: 0.6585, Val Loss: 1.3153, Val Accuracy: 0.5893 Epoch 3559/10000, Train Loss: 1.2544, Train Accuracy: 0.6663, Val Loss: 1.3151, Val Accuracy: 0.5893 Epoch 3560/10000, Train Loss: 1.2550, Train Accuracy: 0.6808, Val Loss: 1.3151, Val Accuracy: 0.5893 Epoch 3561/10000, Train Loss: 1.2489, Train Accuracy: 0.6830, Val Loss: 1.3151, Val Accuracy: 0.5893 Epoch 3562/10000, Train Loss: 1.2555, Train Accuracy: 0.6797, Val Loss: 1.3151, Val Accuracy: 0.5893 Epoch 3563/10000, Train Loss: 1.2541, Train Accuracy: 0.6585, Val Loss: 1.3150, Val Accuracy: 0.5893 Epoch 3564/10000, Train Loss: 1.2550, Train Accuracy: 0.6719, Val Loss: 1.3150, Val Accuracy: 0.5893 Epoch 3565/10000, Train Loss: 1.2603, Train Accuracy: 0.6629, Val Loss: 1.3149, Val Accuracy: 0.5893 Epoch 3566/10000, Train Loss: 1.2518, Train Accuracy: 0.6752, Val Loss: 1.3149, Val Accuracy: 0.5848 Epoch 3567/10000, Train Loss: 1.2571, Train Accuracy: 0.6730, Val Loss: 1.3148, Val Accuracy: 0.5848 Epoch 3568/10000, Train Loss: 1.2654, Train Accuracy: 0.6618, Val Loss: 1.3147, Val Accuracy: 0.5848 Epoch 3569/10000, Train Loss: 1.2607, Train Accuracy: 0.6696, Val Loss: 1.3147, Val Accuracy: 0.5848 Epoch 3570/10000, Train Loss: 1.2568, Train Accuracy: 0.6708, Val Loss: 1.3146, Val Accuracy: 0.5848 Epoch 3571/10000, Train Loss: 1.2475, Train Accuracy: 0.6908, Val Loss: 1.3146, Val Accuracy: 0.5848 Epoch 3572/10000, Train Loss: 1.2563, Train Accuracy: 0.6685, Val Loss: 1.3144, Val Accuracy: 0.5848 Epoch 3573/10000, Train Loss: 1.2600, Train Accuracy: 0.6629, Val Loss: 1.3144, Val Accuracy: 0.5848 Epoch 3574/10000, Train Loss: 1.2604, Train Accuracy: 0.6663, Val Loss: 1.3143, Val Accuracy: 0.5848 Epoch 3575/10000, Train Loss: 1.2599, Train Accuracy: 0.6562, Val Loss: 1.3143, Val Accuracy: 0.5848 Epoch 3576/10000, Train Loss: 1.2551, Train Accuracy: 0.6763, Val Loss: 1.3142, Val Accuracy: 0.5804 Epoch 3577/10000, Train Loss: 1.2514, Train Accuracy: 0.6652, Val Loss: 1.3141, Val Accuracy: 0.5804 Epoch 3578/10000, Train Loss: 1.2555, Train Accuracy: 0.6663, Val Loss: 1.3141, Val Accuracy: 0.5804 Epoch 3579/10000, Train Loss: 1.2585, Train Accuracy: 0.6618, Val Loss: 1.3141, Val Accuracy: 0.5804 Epoch 3580/10000, Train Loss: 1.2568, Train Accuracy: 0.6741, Val Loss: 1.3142, Val Accuracy: 0.5848 Epoch 3581/10000, Train Loss: 1.2623, Train Accuracy: 0.6540, Val Loss: 1.3141, Val Accuracy: 0.5804 Epoch 3582/10000, Train Loss: 1.2557, Train Accuracy: 0.6674, Val Loss: 1.3140, Val Accuracy: 0.5804 Epoch 3583/10000, Train Loss: 1.2456, Train Accuracy: 0.6797, Val Loss: 1.3140, Val Accuracy: 0.5848 Epoch 3584/10000, Train Loss: 1.2563, Train Accuracy: 0.6786, Val Loss: 1.3141, Val Accuracy: 0.5848 Epoch 3585/10000, Train Loss: 1.2611, Train Accuracy: 0.6551, Val Loss: 1.3141, Val Accuracy: 0.5848 Epoch 3586/10000, Train Loss: 1.2381, Train Accuracy: 0.6920, Val Loss: 1.3140, Val Accuracy: 0.5848 Epoch 3587/10000, Train Loss: 1.2541, Train Accuracy: 0.6663, Val Loss: 1.3139, Val Accuracy: 0.5848 Epoch 3588/10000, Train Loss: 1.2536, Train Accuracy: 0.6763, Val Loss: 1.3139, Val Accuracy: 0.5804 Epoch 3589/10000, Train Loss: 1.2489, Train Accuracy: 0.6708, Val Loss: 1.3138, Val Accuracy: 0.5804 Epoch 3590/10000, Train Loss: 1.2568, Train Accuracy: 0.6719, Val Loss: 1.3138, Val Accuracy: 0.5848 Epoch 3591/10000, Train Loss: 1.2623, Train Accuracy: 0.6652, Val Loss: 1.3137, Val Accuracy: 0.5804 Epoch 3592/10000, Train Loss: 1.2553, Train Accuracy: 0.6741, Val Loss: 1.3136, Val Accuracy: 0.5804 Epoch 3593/10000, Train Loss: 1.2528, Train Accuracy: 0.6708, Val Loss: 1.3136, Val Accuracy: 0.5804 Epoch 3594/10000, Train Loss: 1.2516, Train Accuracy: 0.6730, Val Loss: 1.3135, Val Accuracy: 0.5804 Epoch 3595/10000, Train Loss: 1.2516, Train Accuracy: 0.6696, Val Loss: 1.3133, Val Accuracy: 0.5804 Epoch 3596/10000, Train Loss: 1.2597, Train Accuracy: 0.6540, Val Loss: 1.3132, Val Accuracy: 0.5804 Epoch 3597/10000, Train Loss: 1.2438, Train Accuracy: 0.6853, Val Loss: 1.3131, Val Accuracy: 0.5804 Epoch 3598/10000, Train Loss: 1.2507, Train Accuracy: 0.6652, Val Loss: 1.3131, Val Accuracy: 0.5804 Epoch 3599/10000, Train Loss: 1.2451, Train Accuracy: 0.6908, Val Loss: 1.3130, Val Accuracy: 0.5804 Epoch 3600/10000, Train Loss: 1.2619, Train Accuracy: 0.6585, Val Loss: 1.3130, Val Accuracy: 0.5804 Epoch 3601/10000, Train Loss: 1.2509, Train Accuracy: 0.6730, Val Loss: 1.3130, Val Accuracy: 0.5804 Epoch 3602/10000, Train Loss: 1.2464, Train Accuracy: 0.6708, Val Loss: 1.3129, Val Accuracy: 0.5804 Epoch 3603/10000, Train Loss: 1.2400, Train Accuracy: 0.6819, Val Loss: 1.3128, Val Accuracy: 0.5804 Epoch 3604/10000, Train Loss: 1.2473, Train Accuracy: 0.6775, Val Loss: 1.3128, Val Accuracy: 0.5804 Epoch 3605/10000, Train Loss: 1.2569, Train Accuracy: 0.6607, Val Loss: 1.3128, Val Accuracy: 0.5848 Epoch 3606/10000, Train Loss: 1.2559, Train Accuracy: 0.6741, Val Loss: 1.3128, Val Accuracy: 0.5848 Epoch 3607/10000, Train Loss: 1.2560, Train Accuracy: 0.6685, Val Loss: 1.3128, Val Accuracy: 0.5848 Epoch 3608/10000, Train Loss: 1.2476, Train Accuracy: 0.6719, Val Loss: 1.3127, Val Accuracy: 0.5848 Epoch 3609/10000, Train Loss: 1.2506, Train Accuracy: 0.6819, Val Loss: 1.3127, Val Accuracy: 0.5848 Epoch 3610/10000, Train Loss: 1.2537, Train Accuracy: 0.6808, Val Loss: 1.3127, Val Accuracy: 0.5848 Epoch 3611/10000, Train Loss: 1.2576, Train Accuracy: 0.6674, Val Loss: 1.3127, Val Accuracy: 0.5848 Epoch 3612/10000, Train Loss: 1.2555, Train Accuracy: 0.6696, Val Loss: 1.3126, Val Accuracy: 0.5848 Epoch 3613/10000, Train Loss: 1.2527, Train Accuracy: 0.6708, Val Loss: 1.3125, Val Accuracy: 0.5848 Epoch 3614/10000, Train Loss: 1.2467, Train Accuracy: 0.6797, Val Loss: 1.3124, Val Accuracy: 0.5848 Epoch 3615/10000, Train Loss: 1.2491, Train Accuracy: 0.6775, Val Loss: 1.3124, Val Accuracy: 0.5848 Epoch 3616/10000, Train Loss: 1.2647, Train Accuracy: 0.6629, Val Loss: 1.3123, Val Accuracy: 0.5848 Epoch 3617/10000, Train Loss: 1.2525, Train Accuracy: 0.6685, Val Loss: 1.3123, Val Accuracy: 0.5848 Epoch 3618/10000, Train Loss: 1.2538, Train Accuracy: 0.6741, Val Loss: 1.3122, Val Accuracy: 0.5848 Epoch 3619/10000, Train Loss: 1.2422, Train Accuracy: 0.6819, Val Loss: 1.3122, Val Accuracy: 0.5848 Epoch 3620/10000, Train Loss: 1.2594, Train Accuracy: 0.6708, Val Loss: 1.3123, Val Accuracy: 0.5848 Epoch 3621/10000, Train Loss: 1.2495, Train Accuracy: 0.6830, Val Loss: 1.3121, Val Accuracy: 0.5848 Epoch 3622/10000, Train Loss: 1.2520, Train Accuracy: 0.6719, Val Loss: 1.3120, Val Accuracy: 0.5848 Epoch 3623/10000, Train Loss: 1.2526, Train Accuracy: 0.6931, Val Loss: 1.3119, Val Accuracy: 0.5848 Epoch 3624/10000, Train Loss: 1.2551, Train Accuracy: 0.6763, Val Loss: 1.3119, Val Accuracy: 0.5848 Epoch 3625/10000, Train Loss: 1.2513, Train Accuracy: 0.6685, Val Loss: 1.3118, Val Accuracy: 0.5848 Epoch 3626/10000, Train Loss: 1.2514, Train Accuracy: 0.6719, Val Loss: 1.3117, Val Accuracy: 0.5848 Epoch 3627/10000, Train Loss: 1.2498, Train Accuracy: 0.6886, Val Loss: 1.3118, Val Accuracy: 0.5848 Epoch 3628/10000, Train Loss: 1.2526, Train Accuracy: 0.6652, Val Loss: 1.3117, Val Accuracy: 0.5848 Epoch 3629/10000, Train Loss: 1.2486, Train Accuracy: 0.6730, Val Loss: 1.3116, Val Accuracy: 0.5848 Epoch 3630/10000, Train Loss: 1.2497, Train Accuracy: 0.6808, Val Loss: 1.3115, Val Accuracy: 0.5848 Epoch 3631/10000, Train Loss: 1.2437, Train Accuracy: 0.6842, Val Loss: 1.3115, Val Accuracy: 0.5848 Epoch 3632/10000, Train Loss: 1.2383, Train Accuracy: 0.6920, Val Loss: 1.3116, Val Accuracy: 0.5848 Epoch 3633/10000, Train Loss: 1.2399, Train Accuracy: 0.6808, Val Loss: 1.3115, Val Accuracy: 0.5848 Epoch 3634/10000, Train Loss: 1.2499, Train Accuracy: 0.6864, Val Loss: 1.3114, Val Accuracy: 0.5848 Epoch 3635/10000, Train Loss: 1.2659, Train Accuracy: 0.6484, Val Loss: 1.3114, Val Accuracy: 0.5848 Epoch 3636/10000, Train Loss: 1.2449, Train Accuracy: 0.6830, Val Loss: 1.3113, Val Accuracy: 0.5848 Epoch 3637/10000, Train Loss: 1.2544, Train Accuracy: 0.6741, Val Loss: 1.3113, Val Accuracy: 0.5848 Epoch 3638/10000, Train Loss: 1.2448, Train Accuracy: 0.6853, Val Loss: 1.3113, Val Accuracy: 0.5848 Epoch 3639/10000, Train Loss: 1.2391, Train Accuracy: 0.6931, Val Loss: 1.3112, Val Accuracy: 0.5848 Epoch 3640/10000, Train Loss: 1.2501, Train Accuracy: 0.6752, Val Loss: 1.3110, Val Accuracy: 0.5848 Epoch 3641/10000, Train Loss: 1.2393, Train Accuracy: 0.6842, Val Loss: 1.3110, Val Accuracy: 0.5848 Epoch 3642/10000, Train Loss: 1.2483, Train Accuracy: 0.6730, Val Loss: 1.3108, Val Accuracy: 0.5848 Epoch 3643/10000, Train Loss: 1.2500, Train Accuracy: 0.6775, Val Loss: 1.3109, Val Accuracy: 0.5848 Epoch 3644/10000, Train Loss: 1.2497, Train Accuracy: 0.6674, Val Loss: 1.3108, Val Accuracy: 0.5848 Epoch 3645/10000, Train Loss: 1.2385, Train Accuracy: 0.7042, Val Loss: 1.3108, Val Accuracy: 0.5848 Epoch 3646/10000, Train Loss: 1.2501, Train Accuracy: 0.6719, Val Loss: 1.3107, Val Accuracy: 0.5848 Epoch 3647/10000, Train Loss: 1.2497, Train Accuracy: 0.6875, Val Loss: 1.3106, Val Accuracy: 0.5848 Epoch 3648/10000, Train Loss: 1.2599, Train Accuracy: 0.6696, Val Loss: 1.3106, Val Accuracy: 0.5848 Epoch 3649/10000, Train Loss: 1.2428, Train Accuracy: 0.6842, Val Loss: 1.3106, Val Accuracy: 0.5848 Epoch 3650/10000, Train Loss: 1.2557, Train Accuracy: 0.6674, Val Loss: 1.3106, Val Accuracy: 0.5848 Epoch 3651/10000, Train Loss: 1.2650, Train Accuracy: 0.6596, Val Loss: 1.3105, Val Accuracy: 0.5848 Epoch 3652/10000, Train Loss: 1.2539, Train Accuracy: 0.6652, Val Loss: 1.3105, Val Accuracy: 0.5848 Epoch 3653/10000, Train Loss: 1.2355, Train Accuracy: 0.6908, Val Loss: 1.3106, Val Accuracy: 0.5848 Epoch 3654/10000, Train Loss: 1.2486, Train Accuracy: 0.6897, Val Loss: 1.3104, Val Accuracy: 0.5848 Epoch 3655/10000, Train Loss: 1.2350, Train Accuracy: 0.6975, Val Loss: 1.3105, Val Accuracy: 0.5848 Epoch 3656/10000, Train Loss: 1.2531, Train Accuracy: 0.6629, Val Loss: 1.3104, Val Accuracy: 0.5848 Epoch 3657/10000, Train Loss: 1.2411, Train Accuracy: 0.6875, Val Loss: 1.3104, Val Accuracy: 0.5848 Epoch 3658/10000, Train Loss: 1.2525, Train Accuracy: 0.6696, Val Loss: 1.3103, Val Accuracy: 0.5848 Epoch 3659/10000, Train Loss: 1.2453, Train Accuracy: 0.6730, Val Loss: 1.3102, Val Accuracy: 0.5848 Epoch 3660/10000, Train Loss: 1.2464, Train Accuracy: 0.6842, Val Loss: 1.3101, Val Accuracy: 0.5848 Epoch 3661/10000, Train Loss: 1.2541, Train Accuracy: 0.6663, Val Loss: 1.3101, Val Accuracy: 0.5848 Epoch 3662/10000, Train Loss: 1.2560, Train Accuracy: 0.6629, Val Loss: 1.3100, Val Accuracy: 0.5848 Epoch 3663/10000, Train Loss: 1.2501, Train Accuracy: 0.6696, Val Loss: 1.3099, Val Accuracy: 0.5848 Epoch 3664/10000, Train Loss: 1.2406, Train Accuracy: 0.6819, Val Loss: 1.3098, Val Accuracy: 0.5848 Epoch 3665/10000, Train Loss: 1.2528, Train Accuracy: 0.6730, Val Loss: 1.3097, Val Accuracy: 0.5848 Epoch 3666/10000, Train Loss: 1.2424, Train Accuracy: 0.6987, Val Loss: 1.3096, Val Accuracy: 0.5848 Epoch 3667/10000, Train Loss: 1.2459, Train Accuracy: 0.6931, Val Loss: 1.3096, Val Accuracy: 0.5848 Epoch 3668/10000, Train Loss: 1.2393, Train Accuracy: 0.6819, Val Loss: 1.3095, Val Accuracy: 0.5848 Epoch 3669/10000, Train Loss: 1.2413, Train Accuracy: 0.6886, Val Loss: 1.3095, Val Accuracy: 0.5848 Epoch 3670/10000, Train Loss: 1.2503, Train Accuracy: 0.6763, Val Loss: 1.3094, Val Accuracy: 0.5848 Epoch 3671/10000, Train Loss: 1.2559, Train Accuracy: 0.6652, Val Loss: 1.3092, Val Accuracy: 0.5848 Epoch 3672/10000, Train Loss: 1.2548, Train Accuracy: 0.6696, Val Loss: 1.3092, Val Accuracy: 0.5848 Epoch 3673/10000, Train Loss: 1.2572, Train Accuracy: 0.6574, Val Loss: 1.3091, Val Accuracy: 0.5848 Epoch 3674/10000, Train Loss: 1.2506, Train Accuracy: 0.6641, Val Loss: 1.3091, Val Accuracy: 0.5848 Epoch 3675/10000, Train Loss: 1.2542, Train Accuracy: 0.6708, Val Loss: 1.3090, Val Accuracy: 0.5848 Epoch 3676/10000, Train Loss: 1.2475, Train Accuracy: 0.6708, Val Loss: 1.3090, Val Accuracy: 0.5848 Epoch 3677/10000, Train Loss: 1.2562, Train Accuracy: 0.6763, Val Loss: 1.3090, Val Accuracy: 0.5848 Epoch 3678/10000, Train Loss: 1.2475, Train Accuracy: 0.6652, Val Loss: 1.3089, Val Accuracy: 0.5848 Epoch 3679/10000, Train Loss: 1.2389, Train Accuracy: 0.6864, Val Loss: 1.3089, Val Accuracy: 0.5848 Epoch 3680/10000, Train Loss: 1.2409, Train Accuracy: 0.6864, Val Loss: 1.3088, Val Accuracy: 0.5848 Epoch 3681/10000, Train Loss: 1.2330, Train Accuracy: 0.6975, Val Loss: 1.3087, Val Accuracy: 0.5848 Epoch 3682/10000, Train Loss: 1.2472, Train Accuracy: 0.6775, Val Loss: 1.3087, Val Accuracy: 0.5848 Epoch 3683/10000, Train Loss: 1.2594, Train Accuracy: 0.6551, Val Loss: 1.3086, Val Accuracy: 0.5848 Epoch 3684/10000, Train Loss: 1.2426, Train Accuracy: 0.6886, Val Loss: 1.3086, Val Accuracy: 0.5848 Epoch 3685/10000, Train Loss: 1.2533, Train Accuracy: 0.6730, Val Loss: 1.3085, Val Accuracy: 0.5848 Epoch 3686/10000, Train Loss: 1.2499, Train Accuracy: 0.6786, Val Loss: 1.3084, Val Accuracy: 0.5848 Epoch 3687/10000, Train Loss: 1.2468, Train Accuracy: 0.6853, Val Loss: 1.3084, Val Accuracy: 0.5848 Epoch 3688/10000, Train Loss: 1.2428, Train Accuracy: 0.6875, Val Loss: 1.3083, Val Accuracy: 0.5893 Epoch 3689/10000, Train Loss: 1.2499, Train Accuracy: 0.6708, Val Loss: 1.3083, Val Accuracy: 0.5938 Epoch 3690/10000, Train Loss: 1.2421, Train Accuracy: 0.6987, Val Loss: 1.3083, Val Accuracy: 0.5893 Epoch 3691/10000, Train Loss: 1.2369, Train Accuracy: 0.6908, Val Loss: 1.3082, Val Accuracy: 0.5848 Epoch 3692/10000, Train Loss: 1.2412, Train Accuracy: 0.6987, Val Loss: 1.3082, Val Accuracy: 0.5848 Epoch 3693/10000, Train Loss: 1.2523, Train Accuracy: 0.6629, Val Loss: 1.3081, Val Accuracy: 0.5848 Epoch 3694/10000, Train Loss: 1.2556, Train Accuracy: 0.6618, Val Loss: 1.3080, Val Accuracy: 0.5848 Epoch 3695/10000, Train Loss: 1.2399, Train Accuracy: 0.6964, Val Loss: 1.3080, Val Accuracy: 0.5848 Epoch 3696/10000, Train Loss: 1.2513, Train Accuracy: 0.6730, Val Loss: 1.3080, Val Accuracy: 0.5848 Epoch 3697/10000, Train Loss: 1.2378, Train Accuracy: 0.6942, Val Loss: 1.3080, Val Accuracy: 0.5848 Epoch 3698/10000, Train Loss: 1.2383, Train Accuracy: 0.6931, Val Loss: 1.3080, Val Accuracy: 0.5848 Epoch 3699/10000, Train Loss: 1.2276, Train Accuracy: 0.6987, Val Loss: 1.3079, Val Accuracy: 0.5848 Epoch 3700/10000, Train Loss: 1.2450, Train Accuracy: 0.6875, Val Loss: 1.3078, Val Accuracy: 0.5848 Epoch 3701/10000, Train Loss: 1.2529, Train Accuracy: 0.6730, Val Loss: 1.3077, Val Accuracy: 0.5848 Epoch 3702/10000, Train Loss: 1.2458, Train Accuracy: 0.6730, Val Loss: 1.3076, Val Accuracy: 0.5848 Epoch 3703/10000, Train Loss: 1.2442, Train Accuracy: 0.6752, Val Loss: 1.3076, Val Accuracy: 0.5848 Epoch 3704/10000, Train Loss: 1.2497, Train Accuracy: 0.6708, Val Loss: 1.3076, Val Accuracy: 0.5848 Epoch 3705/10000, Train Loss: 1.2541, Train Accuracy: 0.6652, Val Loss: 1.3076, Val Accuracy: 0.5848 Epoch 3706/10000, Train Loss: 1.2428, Train Accuracy: 0.6842, Val Loss: 1.3076, Val Accuracy: 0.5848 Epoch 3707/10000, Train Loss: 1.2490, Train Accuracy: 0.6752, Val Loss: 1.3075, Val Accuracy: 0.5848 Epoch 3708/10000, Train Loss: 1.2458, Train Accuracy: 0.6763, Val Loss: 1.3074, Val Accuracy: 0.5848 Epoch 3709/10000, Train Loss: 1.2443, Train Accuracy: 0.6752, Val Loss: 1.3073, Val Accuracy: 0.5848 Epoch 3710/10000, Train Loss: 1.2455, Train Accuracy: 0.6708, Val Loss: 1.3074, Val Accuracy: 0.5848 Epoch 3711/10000, Train Loss: 1.2350, Train Accuracy: 0.6920, Val Loss: 1.3072, Val Accuracy: 0.5848 Epoch 3712/10000, Train Loss: 1.2531, Train Accuracy: 0.6719, Val Loss: 1.3072, Val Accuracy: 0.5848 Epoch 3713/10000, Train Loss: 1.2456, Train Accuracy: 0.6808, Val Loss: 1.3073, Val Accuracy: 0.5848 Epoch 3714/10000, Train Loss: 1.2376, Train Accuracy: 0.6864, Val Loss: 1.3073, Val Accuracy: 0.5848 Epoch 3715/10000, Train Loss: 1.2336, Train Accuracy: 0.6920, Val Loss: 1.3072, Val Accuracy: 0.5848 Epoch 3716/10000, Train Loss: 1.2339, Train Accuracy: 0.6920, Val Loss: 1.3071, Val Accuracy: 0.5848 Epoch 3717/10000, Train Loss: 1.2373, Train Accuracy: 0.6908, Val Loss: 1.3071, Val Accuracy: 0.5848 Epoch 3718/10000, Train Loss: 1.2394, Train Accuracy: 0.6853, Val Loss: 1.3071, Val Accuracy: 0.5848 Epoch 3719/10000, Train Loss: 1.2553, Train Accuracy: 0.6763, Val Loss: 1.3071, Val Accuracy: 0.5848 Epoch 3720/10000, Train Loss: 1.2392, Train Accuracy: 0.6830, Val Loss: 1.3071, Val Accuracy: 0.5848 Epoch 3721/10000, Train Loss: 1.2593, Train Accuracy: 0.6540, Val Loss: 1.3070, Val Accuracy: 0.5848 Epoch 3722/10000, Train Loss: 1.2378, Train Accuracy: 0.6875, Val Loss: 1.3069, Val Accuracy: 0.5848 Epoch 3723/10000, Train Loss: 1.2455, Train Accuracy: 0.6842, Val Loss: 1.3068, Val Accuracy: 0.5848 Epoch 3724/10000, Train Loss: 1.2473, Train Accuracy: 0.6652, Val Loss: 1.3067, Val Accuracy: 0.5848 Epoch 3725/10000, Train Loss: 1.2416, Train Accuracy: 0.6775, Val Loss: 1.3067, Val Accuracy: 0.5848 Epoch 3726/10000, Train Loss: 1.2479, Train Accuracy: 0.6775, Val Loss: 1.3067, Val Accuracy: 0.5848 Epoch 3727/10000, Train Loss: 1.2313, Train Accuracy: 0.7009, Val Loss: 1.3066, Val Accuracy: 0.5848 Epoch 3728/10000, Train Loss: 1.2466, Train Accuracy: 0.6808, Val Loss: 1.3066, Val Accuracy: 0.5848 Epoch 3729/10000, Train Loss: 1.2473, Train Accuracy: 0.6786, Val Loss: 1.3067, Val Accuracy: 0.5848 Epoch 3730/10000, Train Loss: 1.2390, Train Accuracy: 0.6775, Val Loss: 1.3065, Val Accuracy: 0.5848 Epoch 3731/10000, Train Loss: 1.2336, Train Accuracy: 0.6830, Val Loss: 1.3064, Val Accuracy: 0.5848 Epoch 3732/10000, Train Loss: 1.2499, Train Accuracy: 0.6663, Val Loss: 1.3064, Val Accuracy: 0.5848 Epoch 3733/10000, Train Loss: 1.2392, Train Accuracy: 0.6953, Val Loss: 1.3063, Val Accuracy: 0.5848 Epoch 3734/10000, Train Loss: 1.2391, Train Accuracy: 0.6853, Val Loss: 1.3063, Val Accuracy: 0.5848 Epoch 3735/10000, Train Loss: 1.2369, Train Accuracy: 0.6808, Val Loss: 1.3063, Val Accuracy: 0.5848 Epoch 3736/10000, Train Loss: 1.2416, Train Accuracy: 0.6797, Val Loss: 1.3063, Val Accuracy: 0.5848 Epoch 3737/10000, Train Loss: 1.2475, Train Accuracy: 0.6819, Val Loss: 1.3062, Val Accuracy: 0.5848 Epoch 3738/10000, Train Loss: 1.2335, Train Accuracy: 0.6931, Val Loss: 1.3061, Val Accuracy: 0.5848 Epoch 3739/10000, Train Loss: 1.2417, Train Accuracy: 0.6897, Val Loss: 1.3060, Val Accuracy: 0.5893 Epoch 3740/10000, Train Loss: 1.2360, Train Accuracy: 0.6897, Val Loss: 1.3061, Val Accuracy: 0.5848 Epoch 3741/10000, Train Loss: 1.2493, Train Accuracy: 0.6652, Val Loss: 1.3060, Val Accuracy: 0.5848 Epoch 3742/10000, Train Loss: 1.2340, Train Accuracy: 0.6786, Val Loss: 1.3060, Val Accuracy: 0.5848 Epoch 3743/10000, Train Loss: 1.2378, Train Accuracy: 0.6797, Val Loss: 1.3060, Val Accuracy: 0.5848 Epoch 3744/10000, Train Loss: 1.2428, Train Accuracy: 0.6953, Val Loss: 1.3059, Val Accuracy: 0.5848 Epoch 3745/10000, Train Loss: 1.2326, Train Accuracy: 0.6931, Val Loss: 1.3059, Val Accuracy: 0.5848 Epoch 3746/10000, Train Loss: 1.2440, Train Accuracy: 0.6775, Val Loss: 1.3058, Val Accuracy: 0.5893 Epoch 3747/10000, Train Loss: 1.2426, Train Accuracy: 0.6741, Val Loss: 1.3058, Val Accuracy: 0.5848 Epoch 3748/10000, Train Loss: 1.2411, Train Accuracy: 0.6920, Val Loss: 1.3058, Val Accuracy: 0.5848 Epoch 3749/10000, Train Loss: 1.2433, Train Accuracy: 0.6763, Val Loss: 1.3058, Val Accuracy: 0.5848 Epoch 3750/10000, Train Loss: 1.2439, Train Accuracy: 0.6864, Val Loss: 1.3058, Val Accuracy: 0.5848 Epoch 3751/10000, Train Loss: 1.2385, Train Accuracy: 0.6808, Val Loss: 1.3058, Val Accuracy: 0.5848 Epoch 3752/10000, Train Loss: 1.2436, Train Accuracy: 0.6797, Val Loss: 1.3057, Val Accuracy: 0.5848 Epoch 3753/10000, Train Loss: 1.2424, Train Accuracy: 0.6864, Val Loss: 1.3057, Val Accuracy: 0.5848 Epoch 3754/10000, Train Loss: 1.2404, Train Accuracy: 0.6875, Val Loss: 1.3057, Val Accuracy: 0.5848 Epoch 3755/10000, Train Loss: 1.2382, Train Accuracy: 0.6920, Val Loss: 1.3057, Val Accuracy: 0.5848 Epoch 3756/10000, Train Loss: 1.2332, Train Accuracy: 0.6942, Val Loss: 1.3057, Val Accuracy: 0.5848 Epoch 3757/10000, Train Loss: 1.2443, Train Accuracy: 0.6775, Val Loss: 1.3057, Val Accuracy: 0.5848 Epoch 3758/10000, Train Loss: 1.2359, Train Accuracy: 0.6942, Val Loss: 1.3056, Val Accuracy: 0.5848 Epoch 3759/10000, Train Loss: 1.2533, Train Accuracy: 0.6618, Val Loss: 1.3056, Val Accuracy: 0.5848 Epoch 3760/10000, Train Loss: 1.2376, Train Accuracy: 0.6897, Val Loss: 1.3055, Val Accuracy: 0.5938 Epoch 3761/10000, Train Loss: 1.2431, Train Accuracy: 0.6819, Val Loss: 1.3054, Val Accuracy: 0.5938 Epoch 3762/10000, Train Loss: 1.2474, Train Accuracy: 0.6797, Val Loss: 1.3054, Val Accuracy: 0.5893 Epoch 3763/10000, Train Loss: 1.2285, Train Accuracy: 0.6931, Val Loss: 1.3053, Val Accuracy: 0.5893 Epoch 3764/10000, Train Loss: 1.2399, Train Accuracy: 0.6842, Val Loss: 1.3052, Val Accuracy: 0.5848 Epoch 3765/10000, Train Loss: 1.2473, Train Accuracy: 0.6875, Val Loss: 1.3051, Val Accuracy: 0.5893 Epoch 3766/10000, Train Loss: 1.2303, Train Accuracy: 0.6964, Val Loss: 1.3050, Val Accuracy: 0.5893 Epoch 3767/10000, Train Loss: 1.2366, Train Accuracy: 0.6908, Val Loss: 1.3050, Val Accuracy: 0.5893 Epoch 3768/10000, Train Loss: 1.2329, Train Accuracy: 0.6853, Val Loss: 1.3049, Val Accuracy: 0.5893 Epoch 3769/10000, Train Loss: 1.2344, Train Accuracy: 0.7054, Val Loss: 1.3049, Val Accuracy: 0.5893 Epoch 3770/10000, Train Loss: 1.2431, Train Accuracy: 0.6830, Val Loss: 1.3048, Val Accuracy: 0.5893 Epoch 3771/10000, Train Loss: 1.2489, Train Accuracy: 0.6741, Val Loss: 1.3047, Val Accuracy: 0.5938 Epoch 3772/10000, Train Loss: 1.2303, Train Accuracy: 0.7009, Val Loss: 1.3047, Val Accuracy: 0.5938 Epoch 3773/10000, Train Loss: 1.2382, Train Accuracy: 0.6975, Val Loss: 1.3047, Val Accuracy: 0.5938 Epoch 3774/10000, Train Loss: 1.2362, Train Accuracy: 0.6864, Val Loss: 1.3046, Val Accuracy: 0.5938 Epoch 3775/10000, Train Loss: 1.2432, Train Accuracy: 0.6830, Val Loss: 1.3045, Val Accuracy: 0.5938 Epoch 3776/10000, Train Loss: 1.2491, Train Accuracy: 0.6752, Val Loss: 1.3045, Val Accuracy: 0.5938 Epoch 3777/10000, Train Loss: 1.2336, Train Accuracy: 0.6875, Val Loss: 1.3045, Val Accuracy: 0.5938 Epoch 3778/10000, Train Loss: 1.2356, Train Accuracy: 0.6875, Val Loss: 1.3043, Val Accuracy: 0.5982 Epoch 3779/10000, Train Loss: 1.2543, Train Accuracy: 0.6685, Val Loss: 1.3041, Val Accuracy: 0.5982 Epoch 3780/10000, Train Loss: 1.2426, Train Accuracy: 0.6741, Val Loss: 1.3040, Val Accuracy: 0.5938 Epoch 3781/10000, Train Loss: 1.2277, Train Accuracy: 0.7065, Val Loss: 1.3039, Val Accuracy: 0.5938 Epoch 3782/10000, Train Loss: 1.2444, Train Accuracy: 0.6696, Val Loss: 1.3039, Val Accuracy: 0.5938 Epoch 3783/10000, Train Loss: 1.2426, Train Accuracy: 0.6830, Val Loss: 1.3038, Val Accuracy: 0.5938 Epoch 3784/10000, Train Loss: 1.2304, Train Accuracy: 0.6920, Val Loss: 1.3037, Val Accuracy: 0.5938 Epoch 3785/10000, Train Loss: 1.2466, Train Accuracy: 0.6663, Val Loss: 1.3038, Val Accuracy: 0.5982 Epoch 3786/10000, Train Loss: 1.2416, Train Accuracy: 0.6708, Val Loss: 1.3037, Val Accuracy: 0.5938 Epoch 3787/10000, Train Loss: 1.2400, Train Accuracy: 0.6797, Val Loss: 1.3037, Val Accuracy: 0.5938 Epoch 3788/10000, Train Loss: 1.2452, Train Accuracy: 0.6674, Val Loss: 1.3036, Val Accuracy: 0.5938 Epoch 3789/10000, Train Loss: 1.2361, Train Accuracy: 0.6897, Val Loss: 1.3037, Val Accuracy: 0.5938 Epoch 3790/10000, Train Loss: 1.2302, Train Accuracy: 0.6998, Val Loss: 1.3037, Val Accuracy: 0.5938 Epoch 3791/10000, Train Loss: 1.2399, Train Accuracy: 0.6797, Val Loss: 1.3036, Val Accuracy: 0.5982 Epoch 3792/10000, Train Loss: 1.2411, Train Accuracy: 0.6864, Val Loss: 1.3035, Val Accuracy: 0.5982 Epoch 3793/10000, Train Loss: 1.2488, Train Accuracy: 0.6652, Val Loss: 1.3034, Val Accuracy: 0.5938 Epoch 3794/10000, Train Loss: 1.2410, Train Accuracy: 0.6719, Val Loss: 1.3034, Val Accuracy: 0.5938 Epoch 3795/10000, Train Loss: 1.2354, Train Accuracy: 0.6908, Val Loss: 1.3034, Val Accuracy: 0.5938 Epoch 3796/10000, Train Loss: 1.2454, Train Accuracy: 0.6663, Val Loss: 1.3034, Val Accuracy: 0.5938 Epoch 3797/10000, Train Loss: 1.2442, Train Accuracy: 0.6786, Val Loss: 1.3033, Val Accuracy: 0.5982 Epoch 3798/10000, Train Loss: 1.2433, Train Accuracy: 0.6786, Val Loss: 1.3032, Val Accuracy: 0.5938 Epoch 3799/10000, Train Loss: 1.2423, Train Accuracy: 0.6853, Val Loss: 1.3030, Val Accuracy: 0.5893 Epoch 3800/10000, Train Loss: 1.2379, Train Accuracy: 0.6819, Val Loss: 1.3030, Val Accuracy: 0.5938 Epoch 3801/10000, Train Loss: 1.2255, Train Accuracy: 0.6953, Val Loss: 1.3029, Val Accuracy: 0.5938 Epoch 3802/10000, Train Loss: 1.2255, Train Accuracy: 0.7009, Val Loss: 1.3029, Val Accuracy: 0.5893 Epoch 3803/10000, Train Loss: 1.2403, Train Accuracy: 0.6830, Val Loss: 1.3028, Val Accuracy: 0.5893 Epoch 3804/10000, Train Loss: 1.2466, Train Accuracy: 0.6752, Val Loss: 1.3027, Val Accuracy: 0.5938 Epoch 3805/10000, Train Loss: 1.2314, Train Accuracy: 0.6864, Val Loss: 1.3027, Val Accuracy: 0.5938 Epoch 3806/10000, Train Loss: 1.2292, Train Accuracy: 0.6942, Val Loss: 1.3027, Val Accuracy: 0.5938 Epoch 3807/10000, Train Loss: 1.2293, Train Accuracy: 0.7042, Val Loss: 1.3027, Val Accuracy: 0.5938 Epoch 3808/10000, Train Loss: 1.2250, Train Accuracy: 0.7020, Val Loss: 1.3026, Val Accuracy: 0.5982 Epoch 3809/10000, Train Loss: 1.2361, Train Accuracy: 0.6786, Val Loss: 1.3027, Val Accuracy: 0.5982 Epoch 3810/10000, Train Loss: 1.2316, Train Accuracy: 0.6853, Val Loss: 1.3024, Val Accuracy: 0.5938 Epoch 3811/10000, Train Loss: 1.2439, Train Accuracy: 0.6719, Val Loss: 1.3024, Val Accuracy: 0.5938 Epoch 3812/10000, Train Loss: 1.2473, Train Accuracy: 0.6730, Val Loss: 1.3024, Val Accuracy: 0.5938 Epoch 3813/10000, Train Loss: 1.2293, Train Accuracy: 0.7031, Val Loss: 1.3024, Val Accuracy: 0.5982 Epoch 3814/10000, Train Loss: 1.2421, Train Accuracy: 0.6920, Val Loss: 1.3023, Val Accuracy: 0.5982 Epoch 3815/10000, Train Loss: 1.2333, Train Accuracy: 0.6763, Val Loss: 1.3022, Val Accuracy: 0.5982 Epoch 3816/10000, Train Loss: 1.2386, Train Accuracy: 0.6864, Val Loss: 1.3022, Val Accuracy: 0.5982 Epoch 3817/10000, Train Loss: 1.2335, Train Accuracy: 0.6908, Val Loss: 1.3021, Val Accuracy: 0.5982 Epoch 3818/10000, Train Loss: 1.2244, Train Accuracy: 0.6998, Val Loss: 1.3021, Val Accuracy: 0.5982 Epoch 3819/10000, Train Loss: 1.2295, Train Accuracy: 0.6953, Val Loss: 1.3020, Val Accuracy: 0.5982 Epoch 3820/10000, Train Loss: 1.2225, Train Accuracy: 0.7109, Val Loss: 1.3021, Val Accuracy: 0.5982 Epoch 3821/10000, Train Loss: 1.2455, Train Accuracy: 0.6685, Val Loss: 1.3020, Val Accuracy: 0.5982 Epoch 3822/10000, Train Loss: 1.2258, Train Accuracy: 0.7020, Val Loss: 1.3020, Val Accuracy: 0.5982 Epoch 3823/10000, Train Loss: 1.2456, Train Accuracy: 0.6529, Val Loss: 1.3019, Val Accuracy: 0.5982 Epoch 3824/10000, Train Loss: 1.2206, Train Accuracy: 0.7042, Val Loss: 1.3019, Val Accuracy: 0.5982 Epoch 3825/10000, Train Loss: 1.2334, Train Accuracy: 0.6920, Val Loss: 1.3018, Val Accuracy: 0.5982 Epoch 3826/10000, Train Loss: 1.2348, Train Accuracy: 0.6964, Val Loss: 1.3017, Val Accuracy: 0.5982 Epoch 3827/10000, Train Loss: 1.2449, Train Accuracy: 0.6685, Val Loss: 1.3017, Val Accuracy: 0.5982 Epoch 3828/10000, Train Loss: 1.2429, Train Accuracy: 0.6775, Val Loss: 1.3017, Val Accuracy: 0.5982 Epoch 3829/10000, Train Loss: 1.2362, Train Accuracy: 0.6931, Val Loss: 1.3016, Val Accuracy: 0.5982 Epoch 3830/10000, Train Loss: 1.2264, Train Accuracy: 0.6953, Val Loss: 1.3014, Val Accuracy: 0.5982 Epoch 3831/10000, Train Loss: 1.2332, Train Accuracy: 0.6964, Val Loss: 1.3013, Val Accuracy: 0.5982 Epoch 3832/10000, Train Loss: 1.2333, Train Accuracy: 0.6864, Val Loss: 1.3012, Val Accuracy: 0.5982 Epoch 3833/10000, Train Loss: 1.2191, Train Accuracy: 0.7188, Val Loss: 1.3012, Val Accuracy: 0.5982 Epoch 3834/10000, Train Loss: 1.2323, Train Accuracy: 0.6842, Val Loss: 1.3011, Val Accuracy: 0.5982 Epoch 3835/10000, Train Loss: 1.2371, Train Accuracy: 0.6830, Val Loss: 1.3011, Val Accuracy: 0.5938 Epoch 3836/10000, Train Loss: 1.2327, Train Accuracy: 0.6897, Val Loss: 1.3011, Val Accuracy: 0.5938 Epoch 3837/10000, Train Loss: 1.2258, Train Accuracy: 0.6931, Val Loss: 1.3009, Val Accuracy: 0.5938 Epoch 3838/10000, Train Loss: 1.2385, Train Accuracy: 0.6853, Val Loss: 1.3008, Val Accuracy: 0.5982 Epoch 3839/10000, Train Loss: 1.2317, Train Accuracy: 0.6853, Val Loss: 1.3008, Val Accuracy: 0.5982 Epoch 3840/10000, Train Loss: 1.2335, Train Accuracy: 0.6975, Val Loss: 1.3007, Val Accuracy: 0.5982 Epoch 3841/10000, Train Loss: 1.2315, Train Accuracy: 0.6987, Val Loss: 1.3007, Val Accuracy: 0.5982 Epoch 3842/10000, Train Loss: 1.2356, Train Accuracy: 0.6931, Val Loss: 1.3006, Val Accuracy: 0.5938 Epoch 3843/10000, Train Loss: 1.2214, Train Accuracy: 0.7076, Val Loss: 1.3005, Val Accuracy: 0.5938 Epoch 3844/10000, Train Loss: 1.2298, Train Accuracy: 0.6942, Val Loss: 1.3005, Val Accuracy: 0.5938 Epoch 3845/10000, Train Loss: 1.2317, Train Accuracy: 0.6942, Val Loss: 1.3005, Val Accuracy: 0.5938 Epoch 3846/10000, Train Loss: 1.2467, Train Accuracy: 0.6730, Val Loss: 1.3004, Val Accuracy: 0.5982 Epoch 3847/10000, Train Loss: 1.2440, Train Accuracy: 0.6786, Val Loss: 1.3004, Val Accuracy: 0.5938 Epoch 3848/10000, Train Loss: 1.2400, Train Accuracy: 0.6842, Val Loss: 1.3004, Val Accuracy: 0.5982 Epoch 3849/10000, Train Loss: 1.2323, Train Accuracy: 0.6920, Val Loss: 1.3003, Val Accuracy: 0.6027 Epoch 3850/10000, Train Loss: 1.2222, Train Accuracy: 0.7087, Val Loss: 1.3002, Val Accuracy: 0.6027 Epoch 3851/10000, Train Loss: 1.2418, Train Accuracy: 0.6663, Val Loss: 1.3001, Val Accuracy: 0.6027 Epoch 3852/10000, Train Loss: 1.2385, Train Accuracy: 0.6819, Val Loss: 1.3002, Val Accuracy: 0.6027 Epoch 3853/10000, Train Loss: 1.2355, Train Accuracy: 0.6819, Val Loss: 1.3002, Val Accuracy: 0.6027 Epoch 3854/10000, Train Loss: 1.2251, Train Accuracy: 0.7065, Val Loss: 1.3002, Val Accuracy: 0.6027 Epoch 3855/10000, Train Loss: 1.2450, Train Accuracy: 0.6775, Val Loss: 1.3001, Val Accuracy: 0.6027 Epoch 3856/10000, Train Loss: 1.2411, Train Accuracy: 0.6842, Val Loss: 1.3000, Val Accuracy: 0.5982 Epoch 3857/10000, Train Loss: 1.2299, Train Accuracy: 0.6931, Val Loss: 1.2999, Val Accuracy: 0.6027 Epoch 3858/10000, Train Loss: 1.2155, Train Accuracy: 0.7165, Val Loss: 1.2999, Val Accuracy: 0.5982 Epoch 3859/10000, Train Loss: 1.2353, Train Accuracy: 0.6864, Val Loss: 1.2997, Val Accuracy: 0.5982 Epoch 3860/10000, Train Loss: 1.2323, Train Accuracy: 0.6875, Val Loss: 1.2997, Val Accuracy: 0.5982 Epoch 3861/10000, Train Loss: 1.2307, Train Accuracy: 0.6920, Val Loss: 1.2995, Val Accuracy: 0.6027 Epoch 3862/10000, Train Loss: 1.2285, Train Accuracy: 0.6953, Val Loss: 1.2996, Val Accuracy: 0.5982 Epoch 3863/10000, Train Loss: 1.2212, Train Accuracy: 0.7054, Val Loss: 1.2995, Val Accuracy: 0.5982 Epoch 3864/10000, Train Loss: 1.2346, Train Accuracy: 0.6964, Val Loss: 1.2995, Val Accuracy: 0.6027 Epoch 3865/10000, Train Loss: 1.2167, Train Accuracy: 0.7121, Val Loss: 1.2994, Val Accuracy: 0.6027 Epoch 3866/10000, Train Loss: 1.2344, Train Accuracy: 0.6920, Val Loss: 1.2994, Val Accuracy: 0.6027 Epoch 3867/10000, Train Loss: 1.2260, Train Accuracy: 0.6953, Val Loss: 1.2994, Val Accuracy: 0.6027 Epoch 3868/10000, Train Loss: 1.2360, Train Accuracy: 0.6830, Val Loss: 1.2993, Val Accuracy: 0.5982 Epoch 3869/10000, Train Loss: 1.2368, Train Accuracy: 0.6886, Val Loss: 1.2993, Val Accuracy: 0.5982 Epoch 3870/10000, Train Loss: 1.2288, Train Accuracy: 0.6931, Val Loss: 1.2993, Val Accuracy: 0.5982 Epoch 3871/10000, Train Loss: 1.2354, Train Accuracy: 0.6964, Val Loss: 1.2991, Val Accuracy: 0.6027 Epoch 3872/10000, Train Loss: 1.2396, Train Accuracy: 0.6842, Val Loss: 1.2991, Val Accuracy: 0.6027 Epoch 3873/10000, Train Loss: 1.2288, Train Accuracy: 0.7054, Val Loss: 1.2992, Val Accuracy: 0.6027 Epoch 3874/10000, Train Loss: 1.2291, Train Accuracy: 0.6886, Val Loss: 1.2991, Val Accuracy: 0.6027 Epoch 3875/10000, Train Loss: 1.2378, Train Accuracy: 0.6975, Val Loss: 1.2991, Val Accuracy: 0.6027 Epoch 3876/10000, Train Loss: 1.2274, Train Accuracy: 0.6897, Val Loss: 1.2990, Val Accuracy: 0.6027 Epoch 3877/10000, Train Loss: 1.2352, Train Accuracy: 0.6908, Val Loss: 1.2989, Val Accuracy: 0.6027 Epoch 3878/10000, Train Loss: 1.2309, Train Accuracy: 0.6864, Val Loss: 1.2988, Val Accuracy: 0.6027 Epoch 3879/10000, Train Loss: 1.2380, Train Accuracy: 0.6864, Val Loss: 1.2989, Val Accuracy: 0.6027 Epoch 3880/10000, Train Loss: 1.2242, Train Accuracy: 0.6920, Val Loss: 1.2988, Val Accuracy: 0.6027 Epoch 3881/10000, Train Loss: 1.2241, Train Accuracy: 0.6975, Val Loss: 1.2988, Val Accuracy: 0.6027 Epoch 3882/10000, Train Loss: 1.2313, Train Accuracy: 0.6908, Val Loss: 1.2987, Val Accuracy: 0.6027 Epoch 3883/10000, Train Loss: 1.2234, Train Accuracy: 0.7042, Val Loss: 1.2986, Val Accuracy: 0.6027 Epoch 3884/10000, Train Loss: 1.2309, Train Accuracy: 0.6908, Val Loss: 1.2986, Val Accuracy: 0.6027 Epoch 3885/10000, Train Loss: 1.2337, Train Accuracy: 0.6797, Val Loss: 1.2985, Val Accuracy: 0.6027 Epoch 3886/10000, Train Loss: 1.2342, Train Accuracy: 0.6886, Val Loss: 1.2984, Val Accuracy: 0.6027 Epoch 3887/10000, Train Loss: 1.2309, Train Accuracy: 0.6875, Val Loss: 1.2983, Val Accuracy: 0.6027 Epoch 3888/10000, Train Loss: 1.2271, Train Accuracy: 0.6886, Val Loss: 1.2983, Val Accuracy: 0.6027 Epoch 3889/10000, Train Loss: 1.2312, Train Accuracy: 0.6908, Val Loss: 1.2982, Val Accuracy: 0.6027 Epoch 3890/10000, Train Loss: 1.2183, Train Accuracy: 0.7154, Val Loss: 1.2982, Val Accuracy: 0.6027 Epoch 3891/10000, Train Loss: 1.2247, Train Accuracy: 0.7098, Val Loss: 1.2981, Val Accuracy: 0.6027 Epoch 3892/10000, Train Loss: 1.2220, Train Accuracy: 0.7098, Val Loss: 1.2981, Val Accuracy: 0.6027 Epoch 3893/10000, Train Loss: 1.2312, Train Accuracy: 0.6853, Val Loss: 1.2979, Val Accuracy: 0.6027 Epoch 3894/10000, Train Loss: 1.2245, Train Accuracy: 0.6931, Val Loss: 1.2978, Val Accuracy: 0.6027 Epoch 3895/10000, Train Loss: 1.2152, Train Accuracy: 0.7132, Val Loss: 1.2978, Val Accuracy: 0.6027 Epoch 3896/10000, Train Loss: 1.2335, Train Accuracy: 0.6908, Val Loss: 1.2978, Val Accuracy: 0.6027 Epoch 3897/10000, Train Loss: 1.2365, Train Accuracy: 0.6897, Val Loss: 1.2977, Val Accuracy: 0.6027 Epoch 3898/10000, Train Loss: 1.2344, Train Accuracy: 0.6775, Val Loss: 1.2977, Val Accuracy: 0.6027 Epoch 3899/10000, Train Loss: 1.2253, Train Accuracy: 0.7009, Val Loss: 1.2976, Val Accuracy: 0.6027 Epoch 3900/10000, Train Loss: 1.2356, Train Accuracy: 0.6875, Val Loss: 1.2976, Val Accuracy: 0.6027 Epoch 3901/10000, Train Loss: 1.2385, Train Accuracy: 0.6685, Val Loss: 1.2975, Val Accuracy: 0.6027 Epoch 3902/10000, Train Loss: 1.2306, Train Accuracy: 0.6975, Val Loss: 1.2976, Val Accuracy: 0.6071 Epoch 3903/10000, Train Loss: 1.2235, Train Accuracy: 0.6964, Val Loss: 1.2975, Val Accuracy: 0.6071 Epoch 3904/10000, Train Loss: 1.2330, Train Accuracy: 0.6864, Val Loss: 1.2974, Val Accuracy: 0.6071 Epoch 3905/10000, Train Loss: 1.2353, Train Accuracy: 0.6819, Val Loss: 1.2975, Val Accuracy: 0.6027 Epoch 3906/10000, Train Loss: 1.2220, Train Accuracy: 0.6964, Val Loss: 1.2976, Val Accuracy: 0.6027 Epoch 3907/10000, Train Loss: 1.2273, Train Accuracy: 0.6942, Val Loss: 1.2974, Val Accuracy: 0.6027 Epoch 3908/10000, Train Loss: 1.2102, Train Accuracy: 0.7176, Val Loss: 1.2973, Val Accuracy: 0.6027 Epoch 3909/10000, Train Loss: 1.2243, Train Accuracy: 0.7109, Val Loss: 1.2973, Val Accuracy: 0.6071 Epoch 3910/10000, Train Loss: 1.2247, Train Accuracy: 0.6964, Val Loss: 1.2972, Val Accuracy: 0.6071 Epoch 3911/10000, Train Loss: 1.2337, Train Accuracy: 0.6942, Val Loss: 1.2970, Val Accuracy: 0.6027 Epoch 3912/10000, Train Loss: 1.2301, Train Accuracy: 0.6819, Val Loss: 1.2971, Val Accuracy: 0.6027 Epoch 3913/10000, Train Loss: 1.2238, Train Accuracy: 0.6998, Val Loss: 1.2970, Val Accuracy: 0.6027 Epoch 3914/10000, Train Loss: 1.2291, Train Accuracy: 0.6886, Val Loss: 1.2969, Val Accuracy: 0.6027 Epoch 3915/10000, Train Loss: 1.2235, Train Accuracy: 0.6964, Val Loss: 1.2968, Val Accuracy: 0.6027 Epoch 3916/10000, Train Loss: 1.2301, Train Accuracy: 0.6998, Val Loss: 1.2969, Val Accuracy: 0.6027 Epoch 3917/10000, Train Loss: 1.2215, Train Accuracy: 0.7042, Val Loss: 1.2968, Val Accuracy: 0.6027 Epoch 3918/10000, Train Loss: 1.2207, Train Accuracy: 0.7054, Val Loss: 1.2968, Val Accuracy: 0.6027 Epoch 3919/10000, Train Loss: 1.2300, Train Accuracy: 0.6842, Val Loss: 1.2968, Val Accuracy: 0.6027 Epoch 3920/10000, Train Loss: 1.2293, Train Accuracy: 0.6830, Val Loss: 1.2967, Val Accuracy: 0.6027 Epoch 3921/10000, Train Loss: 1.2353, Train Accuracy: 0.6864, Val Loss: 1.2968, Val Accuracy: 0.6027 Epoch 3922/10000, Train Loss: 1.2244, Train Accuracy: 0.7109, Val Loss: 1.2968, Val Accuracy: 0.6027 Epoch 3923/10000, Train Loss: 1.2280, Train Accuracy: 0.6853, Val Loss: 1.2967, Val Accuracy: 0.6027 Epoch 3924/10000, Train Loss: 1.2264, Train Accuracy: 0.7031, Val Loss: 1.2966, Val Accuracy: 0.6027 Epoch 3925/10000, Train Loss: 1.2369, Train Accuracy: 0.6808, Val Loss: 1.2966, Val Accuracy: 0.6071 Epoch 3926/10000, Train Loss: 1.2243, Train Accuracy: 0.7065, Val Loss: 1.2965, Val Accuracy: 0.6027 Epoch 3927/10000, Train Loss: 1.2359, Train Accuracy: 0.6853, Val Loss: 1.2965, Val Accuracy: 0.6027 Epoch 3928/10000, Train Loss: 1.2268, Train Accuracy: 0.6953, Val Loss: 1.2965, Val Accuracy: 0.6027 Epoch 3929/10000, Train Loss: 1.2335, Train Accuracy: 0.6897, Val Loss: 1.2963, Val Accuracy: 0.6071 Epoch 3930/10000, Train Loss: 1.2314, Train Accuracy: 0.6864, Val Loss: 1.2963, Val Accuracy: 0.6071 Epoch 3931/10000, Train Loss: 1.2266, Train Accuracy: 0.6964, Val Loss: 1.2962, Val Accuracy: 0.6071 Epoch 3932/10000, Train Loss: 1.2212, Train Accuracy: 0.7065, Val Loss: 1.2961, Val Accuracy: 0.6071 Epoch 3933/10000, Train Loss: 1.2285, Train Accuracy: 0.6942, Val Loss: 1.2961, Val Accuracy: 0.6071 Epoch 3934/10000, Train Loss: 1.2281, Train Accuracy: 0.6931, Val Loss: 1.2961, Val Accuracy: 0.6027 Epoch 3935/10000, Train Loss: 1.2264, Train Accuracy: 0.7065, Val Loss: 1.2961, Val Accuracy: 0.6027 Epoch 3936/10000, Train Loss: 1.2266, Train Accuracy: 0.6842, Val Loss: 1.2961, Val Accuracy: 0.6071 Epoch 3937/10000, Train Loss: 1.2228, Train Accuracy: 0.6875, Val Loss: 1.2962, Val Accuracy: 0.6027 Epoch 3938/10000, Train Loss: 1.2352, Train Accuracy: 0.6853, Val Loss: 1.2961, Val Accuracy: 0.6116 Epoch 3939/10000, Train Loss: 1.2265, Train Accuracy: 0.7031, Val Loss: 1.2961, Val Accuracy: 0.6116 Epoch 3940/10000, Train Loss: 1.2229, Train Accuracy: 0.7042, Val Loss: 1.2961, Val Accuracy: 0.6116 Epoch 3941/10000, Train Loss: 1.2291, Train Accuracy: 0.6953, Val Loss: 1.2960, Val Accuracy: 0.6116 Epoch 3942/10000, Train Loss: 1.2200, Train Accuracy: 0.6975, Val Loss: 1.2959, Val Accuracy: 0.6071 Epoch 3943/10000, Train Loss: 1.2273, Train Accuracy: 0.6987, Val Loss: 1.2959, Val Accuracy: 0.6071 Epoch 3944/10000, Train Loss: 1.2316, Train Accuracy: 0.6931, Val Loss: 1.2958, Val Accuracy: 0.6027 Epoch 3945/10000, Train Loss: 1.2243, Train Accuracy: 0.6953, Val Loss: 1.2958, Val Accuracy: 0.6027 Epoch 3946/10000, Train Loss: 1.2367, Train Accuracy: 0.6908, Val Loss: 1.2957, Val Accuracy: 0.6071 Epoch 3947/10000, Train Loss: 1.2274, Train Accuracy: 0.6942, Val Loss: 1.2956, Val Accuracy: 0.6027 Epoch 3948/10000, Train Loss: 1.2268, Train Accuracy: 0.7009, Val Loss: 1.2956, Val Accuracy: 0.6071 Epoch 3949/10000, Train Loss: 1.2248, Train Accuracy: 0.7109, Val Loss: 1.2955, Val Accuracy: 0.6027 Epoch 3950/10000, Train Loss: 1.2236, Train Accuracy: 0.6953, Val Loss: 1.2955, Val Accuracy: 0.6027 Epoch 3951/10000, Train Loss: 1.2260, Train Accuracy: 0.7054, Val Loss: 1.2954, Val Accuracy: 0.6027 Epoch 3952/10000, Train Loss: 1.2388, Train Accuracy: 0.6786, Val Loss: 1.2953, Val Accuracy: 0.6027 Epoch 3953/10000, Train Loss: 1.2162, Train Accuracy: 0.7065, Val Loss: 1.2953, Val Accuracy: 0.6071 Epoch 3954/10000, Train Loss: 1.2289, Train Accuracy: 0.6842, Val Loss: 1.2954, Val Accuracy: 0.6116 Epoch 3955/10000, Train Loss: 1.2361, Train Accuracy: 0.6752, Val Loss: 1.2953, Val Accuracy: 0.6071 Epoch 3956/10000, Train Loss: 1.2243, Train Accuracy: 0.7020, Val Loss: 1.2952, Val Accuracy: 0.6071 Epoch 3957/10000, Train Loss: 1.2307, Train Accuracy: 0.6920, Val Loss: 1.2951, Val Accuracy: 0.6071 Epoch 3958/10000, Train Loss: 1.2290, Train Accuracy: 0.6842, Val Loss: 1.2950, Val Accuracy: 0.6071 Epoch 3959/10000, Train Loss: 1.2176, Train Accuracy: 0.7121, Val Loss: 1.2951, Val Accuracy: 0.6071 Epoch 3960/10000, Train Loss: 1.2346, Train Accuracy: 0.6886, Val Loss: 1.2949, Val Accuracy: 0.6071 Epoch 3961/10000, Train Loss: 1.2195, Train Accuracy: 0.7109, Val Loss: 1.2948, Val Accuracy: 0.6071 Epoch 3962/10000, Train Loss: 1.2341, Train Accuracy: 0.6763, Val Loss: 1.2948, Val Accuracy: 0.6116 Epoch 3963/10000, Train Loss: 1.2356, Train Accuracy: 0.6830, Val Loss: 1.2946, Val Accuracy: 0.6116 Epoch 3964/10000, Train Loss: 1.2258, Train Accuracy: 0.7009, Val Loss: 1.2945, Val Accuracy: 0.6116 Epoch 3965/10000, Train Loss: 1.2135, Train Accuracy: 0.7121, Val Loss: 1.2944, Val Accuracy: 0.6116 Epoch 3966/10000, Train Loss: 1.2158, Train Accuracy: 0.7076, Val Loss: 1.2943, Val Accuracy: 0.6116 Epoch 3967/10000, Train Loss: 1.2185, Train Accuracy: 0.7087, Val Loss: 1.2943, Val Accuracy: 0.6116 Epoch 3968/10000, Train Loss: 1.2339, Train Accuracy: 0.6886, Val Loss: 1.2943, Val Accuracy: 0.6116 Epoch 3969/10000, Train Loss: 1.2301, Train Accuracy: 0.6953, Val Loss: 1.2944, Val Accuracy: 0.6116 Epoch 3970/10000, Train Loss: 1.2298, Train Accuracy: 0.6908, Val Loss: 1.2943, Val Accuracy: 0.6071 Epoch 3971/10000, Train Loss: 1.2237, Train Accuracy: 0.6987, Val Loss: 1.2942, Val Accuracy: 0.6116 Epoch 3972/10000, Train Loss: 1.2153, Train Accuracy: 0.6975, Val Loss: 1.2941, Val Accuracy: 0.6116 Epoch 3973/10000, Train Loss: 1.2289, Train Accuracy: 0.6897, Val Loss: 1.2941, Val Accuracy: 0.6116 Epoch 3974/10000, Train Loss: 1.2190, Train Accuracy: 0.7042, Val Loss: 1.2940, Val Accuracy: 0.6116 Epoch 3975/10000, Train Loss: 1.2161, Train Accuracy: 0.7065, Val Loss: 1.2940, Val Accuracy: 0.6116 Epoch 3976/10000, Train Loss: 1.2286, Train Accuracy: 0.6886, Val Loss: 1.2939, Val Accuracy: 0.6116 Epoch 3977/10000, Train Loss: 1.2260, Train Accuracy: 0.7031, Val Loss: 1.2938, Val Accuracy: 0.6116 Epoch 3978/10000, Train Loss: 1.2137, Train Accuracy: 0.7065, Val Loss: 1.2939, Val Accuracy: 0.6116 Epoch 3979/10000, Train Loss: 1.2235, Train Accuracy: 0.7054, Val Loss: 1.2938, Val Accuracy: 0.6116 Epoch 3980/10000, Train Loss: 1.2328, Train Accuracy: 0.6752, Val Loss: 1.2938, Val Accuracy: 0.6116 Epoch 3981/10000, Train Loss: 1.2207, Train Accuracy: 0.7076, Val Loss: 1.2937, Val Accuracy: 0.6116 Epoch 3982/10000, Train Loss: 1.2173, Train Accuracy: 0.6953, Val Loss: 1.2937, Val Accuracy: 0.6071 Epoch 3983/10000, Train Loss: 1.2343, Train Accuracy: 0.6864, Val Loss: 1.2936, Val Accuracy: 0.6116 Epoch 3984/10000, Train Loss: 1.2333, Train Accuracy: 0.6920, Val Loss: 1.2935, Val Accuracy: 0.6116 Epoch 3985/10000, Train Loss: 1.2223, Train Accuracy: 0.6975, Val Loss: 1.2935, Val Accuracy: 0.6071 Epoch 3986/10000, Train Loss: 1.2136, Train Accuracy: 0.7098, Val Loss: 1.2935, Val Accuracy: 0.6071 Epoch 3987/10000, Train Loss: 1.2137, Train Accuracy: 0.7065, Val Loss: 1.2935, Val Accuracy: 0.6071 Epoch 3988/10000, Train Loss: 1.2155, Train Accuracy: 0.7143, Val Loss: 1.2934, Val Accuracy: 0.6116 Epoch 3989/10000, Train Loss: 1.2164, Train Accuracy: 0.7154, Val Loss: 1.2934, Val Accuracy: 0.6071 Epoch 3990/10000, Train Loss: 1.2203, Train Accuracy: 0.6987, Val Loss: 1.2933, Val Accuracy: 0.6071 Epoch 3991/10000, Train Loss: 1.2177, Train Accuracy: 0.7031, Val Loss: 1.2932, Val Accuracy: 0.6071 Epoch 3992/10000, Train Loss: 1.2239, Train Accuracy: 0.6886, Val Loss: 1.2932, Val Accuracy: 0.6071 Epoch 3993/10000, Train Loss: 1.2270, Train Accuracy: 0.6897, Val Loss: 1.2931, Val Accuracy: 0.6071 Epoch 3994/10000, Train Loss: 1.2191, Train Accuracy: 0.7076, Val Loss: 1.2930, Val Accuracy: 0.6071 Epoch 3995/10000, Train Loss: 1.2210, Train Accuracy: 0.7065, Val Loss: 1.2928, Val Accuracy: 0.6071 Epoch 3996/10000, Train Loss: 1.2335, Train Accuracy: 0.6864, Val Loss: 1.2928, Val Accuracy: 0.6071 Epoch 3997/10000, Train Loss: 1.2272, Train Accuracy: 0.7031, Val Loss: 1.2927, Val Accuracy: 0.6071 Epoch 3998/10000, Train Loss: 1.2210, Train Accuracy: 0.6998, Val Loss: 1.2928, Val Accuracy: 0.6071 Epoch 3999/10000, Train Loss: 1.2237, Train Accuracy: 0.7042, Val Loss: 1.2927, Val Accuracy: 0.6071 Epoch 4000/10000, Train Loss: 1.2156, Train Accuracy: 0.7076, Val Loss: 1.2928, Val Accuracy: 0.6071 Epoch 4001/10000, Train Loss: 1.2223, Train Accuracy: 0.6908, Val Loss: 1.2928, Val Accuracy: 0.6071 Epoch 4002/10000, Train Loss: 1.2155, Train Accuracy: 0.7165, Val Loss: 1.2929, Val Accuracy: 0.6071 Epoch 4003/10000, Train Loss: 1.2317, Train Accuracy: 0.6830, Val Loss: 1.2928, Val Accuracy: 0.6071 Epoch 4004/10000, Train Loss: 1.2288, Train Accuracy: 0.6853, Val Loss: 1.2927, Val Accuracy: 0.6071 Epoch 4005/10000, Train Loss: 1.2131, Train Accuracy: 0.7154, Val Loss: 1.2925, Val Accuracy: 0.6071 Epoch 4006/10000, Train Loss: 1.2237, Train Accuracy: 0.6920, Val Loss: 1.2924, Val Accuracy: 0.6071 Epoch 4007/10000, Train Loss: 1.2196, Train Accuracy: 0.7054, Val Loss: 1.2924, Val Accuracy: 0.6071 Epoch 4008/10000, Train Loss: 1.2348, Train Accuracy: 0.6775, Val Loss: 1.2924, Val Accuracy: 0.6071 Epoch 4009/10000, Train Loss: 1.2378, Train Accuracy: 0.6685, Val Loss: 1.2925, Val Accuracy: 0.6071 Epoch 4010/10000, Train Loss: 1.2068, Train Accuracy: 0.7188, Val Loss: 1.2922, Val Accuracy: 0.6071 Epoch 4011/10000, Train Loss: 1.2233, Train Accuracy: 0.6920, Val Loss: 1.2922, Val Accuracy: 0.6071 Epoch 4012/10000, Train Loss: 1.2323, Train Accuracy: 0.6853, Val Loss: 1.2923, Val Accuracy: 0.6071 Epoch 4013/10000, Train Loss: 1.2267, Train Accuracy: 0.6819, Val Loss: 1.2923, Val Accuracy: 0.6071 Epoch 4014/10000, Train Loss: 1.2198, Train Accuracy: 0.6964, Val Loss: 1.2922, Val Accuracy: 0.6071 Epoch 4015/10000, Train Loss: 1.2200, Train Accuracy: 0.7065, Val Loss: 1.2921, Val Accuracy: 0.6116 Epoch 4016/10000, Train Loss: 1.2055, Train Accuracy: 0.7199, Val Loss: 1.2920, Val Accuracy: 0.6116 Epoch 4017/10000, Train Loss: 1.2331, Train Accuracy: 0.6808, Val Loss: 1.2919, Val Accuracy: 0.6161 Epoch 4018/10000, Train Loss: 1.2264, Train Accuracy: 0.6819, Val Loss: 1.2919, Val Accuracy: 0.6116 Epoch 4019/10000, Train Loss: 1.2274, Train Accuracy: 0.6830, Val Loss: 1.2918, Val Accuracy: 0.6116 Epoch 4020/10000, Train Loss: 1.2284, Train Accuracy: 0.6875, Val Loss: 1.2918, Val Accuracy: 0.6116 Epoch 4021/10000, Train Loss: 1.2204, Train Accuracy: 0.6964, Val Loss: 1.2917, Val Accuracy: 0.6116 Epoch 4022/10000, Train Loss: 1.2191, Train Accuracy: 0.7020, Val Loss: 1.2917, Val Accuracy: 0.6116 Epoch 4023/10000, Train Loss: 1.2302, Train Accuracy: 0.6931, Val Loss: 1.2917, Val Accuracy: 0.6116 Epoch 4024/10000, Train Loss: 1.2226, Train Accuracy: 0.6942, Val Loss: 1.2916, Val Accuracy: 0.6116 Epoch 4025/10000, Train Loss: 1.2186, Train Accuracy: 0.7042, Val Loss: 1.2915, Val Accuracy: 0.6116 Epoch 4026/10000, Train Loss: 1.2162, Train Accuracy: 0.7009, Val Loss: 1.2915, Val Accuracy: 0.6116 Epoch 4027/10000, Train Loss: 1.2216, Train Accuracy: 0.7065, Val Loss: 1.2916, Val Accuracy: 0.6071 Epoch 4028/10000, Train Loss: 1.2053, Train Accuracy: 0.7154, Val Loss: 1.2915, Val Accuracy: 0.6116 Epoch 4029/10000, Train Loss: 1.2265, Train Accuracy: 0.6998, Val Loss: 1.2914, Val Accuracy: 0.6071 Epoch 4030/10000, Train Loss: 1.2159, Train Accuracy: 0.7042, Val Loss: 1.2913, Val Accuracy: 0.6071 Epoch 4031/10000, Train Loss: 1.2228, Train Accuracy: 0.7020, Val Loss: 1.2914, Val Accuracy: 0.6071 Epoch 4032/10000, Train Loss: 1.2286, Train Accuracy: 0.6875, Val Loss: 1.2914, Val Accuracy: 0.6116 Epoch 4033/10000, Train Loss: 1.2183, Train Accuracy: 0.7065, Val Loss: 1.2913, Val Accuracy: 0.6071 Epoch 4034/10000, Train Loss: 1.2111, Train Accuracy: 0.7065, Val Loss: 1.2914, Val Accuracy: 0.6071 Epoch 4035/10000, Train Loss: 1.2199, Train Accuracy: 0.7076, Val Loss: 1.2912, Val Accuracy: 0.6116 Epoch 4036/10000, Train Loss: 1.2259, Train Accuracy: 0.6964, Val Loss: 1.2911, Val Accuracy: 0.6116 Epoch 4037/10000, Train Loss: 1.2287, Train Accuracy: 0.6920, Val Loss: 1.2910, Val Accuracy: 0.6161 Epoch 4038/10000, Train Loss: 1.2302, Train Accuracy: 0.6886, Val Loss: 1.2909, Val Accuracy: 0.6161 Epoch 4039/10000, Train Loss: 1.2052, Train Accuracy: 0.7199, Val Loss: 1.2909, Val Accuracy: 0.6161 Epoch 4040/10000, Train Loss: 1.2129, Train Accuracy: 0.7176, Val Loss: 1.2909, Val Accuracy: 0.6161 Epoch 4041/10000, Train Loss: 1.2010, Train Accuracy: 0.7210, Val Loss: 1.2908, Val Accuracy: 0.6161 Epoch 4042/10000, Train Loss: 1.2189, Train Accuracy: 0.6964, Val Loss: 1.2908, Val Accuracy: 0.6161 Epoch 4043/10000, Train Loss: 1.2176, Train Accuracy: 0.7031, Val Loss: 1.2906, Val Accuracy: 0.6161 Epoch 4044/10000, Train Loss: 1.2101, Train Accuracy: 0.7188, Val Loss: 1.2906, Val Accuracy: 0.6161 Epoch 4045/10000, Train Loss: 1.2294, Train Accuracy: 0.6897, Val Loss: 1.2905, Val Accuracy: 0.6161 Epoch 4046/10000, Train Loss: 1.2082, Train Accuracy: 0.7221, Val Loss: 1.2904, Val Accuracy: 0.6161 Epoch 4047/10000, Train Loss: 1.2132, Train Accuracy: 0.7054, Val Loss: 1.2903, Val Accuracy: 0.6161 Epoch 4048/10000, Train Loss: 1.2184, Train Accuracy: 0.7076, Val Loss: 1.2904, Val Accuracy: 0.6161 Epoch 4049/10000, Train Loss: 1.2158, Train Accuracy: 0.7087, Val Loss: 1.2904, Val Accuracy: 0.6116 Epoch 4050/10000, Train Loss: 1.2204, Train Accuracy: 0.7031, Val Loss: 1.2903, Val Accuracy: 0.6116 Epoch 4051/10000, Train Loss: 1.2265, Train Accuracy: 0.6920, Val Loss: 1.2903, Val Accuracy: 0.6116 Epoch 4052/10000, Train Loss: 1.2141, Train Accuracy: 0.7020, Val Loss: 1.2902, Val Accuracy: 0.6116 Epoch 4053/10000, Train Loss: 1.2170, Train Accuracy: 0.6975, Val Loss: 1.2900, Val Accuracy: 0.6116 Epoch 4054/10000, Train Loss: 1.2244, Train Accuracy: 0.6975, Val Loss: 1.2900, Val Accuracy: 0.6116 Epoch 4055/10000, Train Loss: 1.2102, Train Accuracy: 0.7154, Val Loss: 1.2899, Val Accuracy: 0.6116 Epoch 4056/10000, Train Loss: 1.2099, Train Accuracy: 0.7221, Val Loss: 1.2900, Val Accuracy: 0.6116 Epoch 4057/10000, Train Loss: 1.2104, Train Accuracy: 0.7098, Val Loss: 1.2899, Val Accuracy: 0.6116 Epoch 4058/10000, Train Loss: 1.2059, Train Accuracy: 0.7176, Val Loss: 1.2899, Val Accuracy: 0.6116 Epoch 4059/10000, Train Loss: 1.2143, Train Accuracy: 0.7165, Val Loss: 1.2899, Val Accuracy: 0.6116 Epoch 4060/10000, Train Loss: 1.2109, Train Accuracy: 0.7132, Val Loss: 1.2897, Val Accuracy: 0.6116 Epoch 4061/10000, Train Loss: 1.2070, Train Accuracy: 0.7109, Val Loss: 1.2897, Val Accuracy: 0.6116 Epoch 4062/10000, Train Loss: 1.2212, Train Accuracy: 0.7031, Val Loss: 1.2896, Val Accuracy: 0.6116 Epoch 4063/10000, Train Loss: 1.2174, Train Accuracy: 0.7042, Val Loss: 1.2896, Val Accuracy: 0.6116 Epoch 4064/10000, Train Loss: 1.2224, Train Accuracy: 0.7042, Val Loss: 1.2896, Val Accuracy: 0.6116 Epoch 4065/10000, Train Loss: 1.2070, Train Accuracy: 0.7188, Val Loss: 1.2897, Val Accuracy: 0.6116 Epoch 4066/10000, Train Loss: 1.2225, Train Accuracy: 0.7009, Val Loss: 1.2898, Val Accuracy: 0.6116 Epoch 4067/10000, Train Loss: 1.2178, Train Accuracy: 0.7020, Val Loss: 1.2897, Val Accuracy: 0.6116 Epoch 4068/10000, Train Loss: 1.2154, Train Accuracy: 0.7087, Val Loss: 1.2895, Val Accuracy: 0.6116 Epoch 4069/10000, Train Loss: 1.2158, Train Accuracy: 0.7031, Val Loss: 1.2894, Val Accuracy: 0.6116 Epoch 4070/10000, Train Loss: 1.2284, Train Accuracy: 0.6853, Val Loss: 1.2893, Val Accuracy: 0.6116 Epoch 4071/10000, Train Loss: 1.2089, Train Accuracy: 0.7165, Val Loss: 1.2892, Val Accuracy: 0.6116 Epoch 4072/10000, Train Loss: 1.2240, Train Accuracy: 0.6942, Val Loss: 1.2891, Val Accuracy: 0.6161 Epoch 4073/10000, Train Loss: 1.2216, Train Accuracy: 0.7031, Val Loss: 1.2891, Val Accuracy: 0.6161 Epoch 4074/10000, Train Loss: 1.2160, Train Accuracy: 0.7087, Val Loss: 1.2891, Val Accuracy: 0.6161 Epoch 4075/10000, Train Loss: 1.2139, Train Accuracy: 0.7009, Val Loss: 1.2890, Val Accuracy: 0.6116 Epoch 4076/10000, Train Loss: 1.2076, Train Accuracy: 0.7098, Val Loss: 1.2890, Val Accuracy: 0.6161 Epoch 4077/10000, Train Loss: 1.2193, Train Accuracy: 0.7031, Val Loss: 1.2889, Val Accuracy: 0.6161 Epoch 4078/10000, Train Loss: 1.2116, Train Accuracy: 0.7132, Val Loss: 1.2888, Val Accuracy: 0.6161 Epoch 4079/10000, Train Loss: 1.2102, Train Accuracy: 0.7121, Val Loss: 1.2886, Val Accuracy: 0.6161 Epoch 4080/10000, Train Loss: 1.2262, Train Accuracy: 0.6786, Val Loss: 1.2887, Val Accuracy: 0.6161 Epoch 4081/10000, Train Loss: 1.2108, Train Accuracy: 0.7076, Val Loss: 1.2885, Val Accuracy: 0.6205 Epoch 4082/10000, Train Loss: 1.2134, Train Accuracy: 0.7165, Val Loss: 1.2886, Val Accuracy: 0.6205 Epoch 4083/10000, Train Loss: 1.2229, Train Accuracy: 0.6953, Val Loss: 1.2886, Val Accuracy: 0.6205 Epoch 4084/10000, Train Loss: 1.2217, Train Accuracy: 0.7020, Val Loss: 1.2887, Val Accuracy: 0.6205 Epoch 4085/10000, Train Loss: 1.2165, Train Accuracy: 0.6975, Val Loss: 1.2886, Val Accuracy: 0.6205 Epoch 4086/10000, Train Loss: 1.2266, Train Accuracy: 0.6908, Val Loss: 1.2885, Val Accuracy: 0.6161 Epoch 4087/10000, Train Loss: 1.2082, Train Accuracy: 0.7132, Val Loss: 1.2885, Val Accuracy: 0.6205 Epoch 4088/10000, Train Loss: 1.2191, Train Accuracy: 0.7054, Val Loss: 1.2885, Val Accuracy: 0.6161 Epoch 4089/10000, Train Loss: 1.2133, Train Accuracy: 0.7165, Val Loss: 1.2884, Val Accuracy: 0.6161 Epoch 4090/10000, Train Loss: 1.2128, Train Accuracy: 0.7009, Val Loss: 1.2884, Val Accuracy: 0.6161 Epoch 4091/10000, Train Loss: 1.2256, Train Accuracy: 0.6908, Val Loss: 1.2883, Val Accuracy: 0.6161 Epoch 4092/10000, Train Loss: 1.2146, Train Accuracy: 0.7121, Val Loss: 1.2882, Val Accuracy: 0.6161 Epoch 4093/10000, Train Loss: 1.2154, Train Accuracy: 0.7054, Val Loss: 1.2882, Val Accuracy: 0.6161 Epoch 4094/10000, Train Loss: 1.2082, Train Accuracy: 0.7199, Val Loss: 1.2881, Val Accuracy: 0.6161 Epoch 4095/10000, Train Loss: 1.2002, Train Accuracy: 0.7254, Val Loss: 1.2881, Val Accuracy: 0.6161 Epoch 4096/10000, Train Loss: 1.2131, Train Accuracy: 0.7054, Val Loss: 1.2880, Val Accuracy: 0.6205 Epoch 4097/10000, Train Loss: 1.2139, Train Accuracy: 0.7076, Val Loss: 1.2879, Val Accuracy: 0.6161 Epoch 4098/10000, Train Loss: 1.2183, Train Accuracy: 0.7042, Val Loss: 1.2881, Val Accuracy: 0.6161 Epoch 4099/10000, Train Loss: 1.2180, Train Accuracy: 0.6897, Val Loss: 1.2881, Val Accuracy: 0.6161 Epoch 4100/10000, Train Loss: 1.2132, Train Accuracy: 0.7109, Val Loss: 1.2882, Val Accuracy: 0.6161 Epoch 4101/10000, Train Loss: 1.2278, Train Accuracy: 0.6920, Val Loss: 1.2880, Val Accuracy: 0.6161 Epoch 4102/10000, Train Loss: 1.2101, Train Accuracy: 0.7176, Val Loss: 1.2879, Val Accuracy: 0.6161 Epoch 4103/10000, Train Loss: 1.2125, Train Accuracy: 0.7054, Val Loss: 1.2878, Val Accuracy: 0.6161 Epoch 4104/10000, Train Loss: 1.2106, Train Accuracy: 0.7109, Val Loss: 1.2878, Val Accuracy: 0.6161 Epoch 4105/10000, Train Loss: 1.2073, Train Accuracy: 0.7087, Val Loss: 1.2876, Val Accuracy: 0.6161 Epoch 4106/10000, Train Loss: 1.2223, Train Accuracy: 0.7020, Val Loss: 1.2875, Val Accuracy: 0.6161 Epoch 4107/10000, Train Loss: 1.2226, Train Accuracy: 0.7020, Val Loss: 1.2874, Val Accuracy: 0.6205 Epoch 4108/10000, Train Loss: 1.2141, Train Accuracy: 0.7154, Val Loss: 1.2873, Val Accuracy: 0.6205 Epoch 4109/10000, Train Loss: 1.2176, Train Accuracy: 0.7020, Val Loss: 1.2872, Val Accuracy: 0.6205 Epoch 4110/10000, Train Loss: 1.2121, Train Accuracy: 0.7143, Val Loss: 1.2871, Val Accuracy: 0.6205 Epoch 4111/10000, Train Loss: 1.2061, Train Accuracy: 0.7087, Val Loss: 1.2869, Val Accuracy: 0.6205 Epoch 4112/10000, Train Loss: 1.2041, Train Accuracy: 0.7176, Val Loss: 1.2868, Val Accuracy: 0.6205 Epoch 4113/10000, Train Loss: 1.2030, Train Accuracy: 0.7299, Val Loss: 1.2868, Val Accuracy: 0.6250 Epoch 4114/10000, Train Loss: 1.2110, Train Accuracy: 0.7065, Val Loss: 1.2867, Val Accuracy: 0.6250 Epoch 4115/10000, Train Loss: 1.2328, Train Accuracy: 0.6786, Val Loss: 1.2865, Val Accuracy: 0.6250 Epoch 4116/10000, Train Loss: 1.2094, Train Accuracy: 0.7121, Val Loss: 1.2865, Val Accuracy: 0.6250 Epoch 4117/10000, Train Loss: 1.2229, Train Accuracy: 0.6998, Val Loss: 1.2864, Val Accuracy: 0.6250 Epoch 4118/10000, Train Loss: 1.2192, Train Accuracy: 0.7009, Val Loss: 1.2863, Val Accuracy: 0.6250 Epoch 4119/10000, Train Loss: 1.2143, Train Accuracy: 0.7076, Val Loss: 1.2863, Val Accuracy: 0.6250 Epoch 4120/10000, Train Loss: 1.2104, Train Accuracy: 0.7165, Val Loss: 1.2863, Val Accuracy: 0.6250 Epoch 4121/10000, Train Loss: 1.2072, Train Accuracy: 0.7143, Val Loss: 1.2862, Val Accuracy: 0.6205 Epoch 4122/10000, Train Loss: 1.2103, Train Accuracy: 0.7176, Val Loss: 1.2862, Val Accuracy: 0.6250 Epoch 4123/10000, Train Loss: 1.2055, Train Accuracy: 0.7254, Val Loss: 1.2861, Val Accuracy: 0.6205 Epoch 4124/10000, Train Loss: 1.2157, Train Accuracy: 0.6975, Val Loss: 1.2861, Val Accuracy: 0.6205 Epoch 4125/10000, Train Loss: 1.1987, Train Accuracy: 0.7299, Val Loss: 1.2860, Val Accuracy: 0.6205 Epoch 4126/10000, Train Loss: 1.2137, Train Accuracy: 0.7154, Val Loss: 1.2860, Val Accuracy: 0.6205 Epoch 4127/10000, Train Loss: 1.2181, Train Accuracy: 0.7065, Val Loss: 1.2859, Val Accuracy: 0.6205 Epoch 4128/10000, Train Loss: 1.2144, Train Accuracy: 0.7143, Val Loss: 1.2857, Val Accuracy: 0.6205 Epoch 4129/10000, Train Loss: 1.2080, Train Accuracy: 0.7109, Val Loss: 1.2857, Val Accuracy: 0.6205 Epoch 4130/10000, Train Loss: 1.2216, Train Accuracy: 0.7042, Val Loss: 1.2857, Val Accuracy: 0.6205 Epoch 4131/10000, Train Loss: 1.2016, Train Accuracy: 0.7277, Val Loss: 1.2857, Val Accuracy: 0.6250 Epoch 4132/10000, Train Loss: 1.2196, Train Accuracy: 0.6975, Val Loss: 1.2856, Val Accuracy: 0.6250 Epoch 4133/10000, Train Loss: 1.2139, Train Accuracy: 0.7165, Val Loss: 1.2855, Val Accuracy: 0.6250 Epoch 4134/10000, Train Loss: 1.2036, Train Accuracy: 0.7210, Val Loss: 1.2854, Val Accuracy: 0.6250 Epoch 4135/10000, Train Loss: 1.2236, Train Accuracy: 0.6931, Val Loss: 1.2853, Val Accuracy: 0.6250 Epoch 4136/10000, Train Loss: 1.2134, Train Accuracy: 0.7042, Val Loss: 1.2853, Val Accuracy: 0.6250 Epoch 4137/10000, Train Loss: 1.2040, Train Accuracy: 0.7254, Val Loss: 1.2853, Val Accuracy: 0.6250 Epoch 4138/10000, Train Loss: 1.2162, Train Accuracy: 0.7065, Val Loss: 1.2853, Val Accuracy: 0.6250 Epoch 4139/10000, Train Loss: 1.2162, Train Accuracy: 0.7031, Val Loss: 1.2854, Val Accuracy: 0.6250 Epoch 4140/10000, Train Loss: 1.2160, Train Accuracy: 0.7087, Val Loss: 1.2853, Val Accuracy: 0.6205 Epoch 4141/10000, Train Loss: 1.2152, Train Accuracy: 0.6998, Val Loss: 1.2854, Val Accuracy: 0.6205 Epoch 4142/10000, Train Loss: 1.2219, Train Accuracy: 0.7031, Val Loss: 1.2853, Val Accuracy: 0.6205 Epoch 4143/10000, Train Loss: 1.2233, Train Accuracy: 0.6942, Val Loss: 1.2852, Val Accuracy: 0.6205 Epoch 4144/10000, Train Loss: 1.2197, Train Accuracy: 0.7020, Val Loss: 1.2851, Val Accuracy: 0.6250 Epoch 4145/10000, Train Loss: 1.2033, Train Accuracy: 0.7154, Val Loss: 1.2851, Val Accuracy: 0.6250 Epoch 4146/10000, Train Loss: 1.2176, Train Accuracy: 0.6987, Val Loss: 1.2852, Val Accuracy: 0.6205 Epoch 4147/10000, Train Loss: 1.2175, Train Accuracy: 0.6964, Val Loss: 1.2851, Val Accuracy: 0.6250 Epoch 4148/10000, Train Loss: 1.2038, Train Accuracy: 0.7344, Val Loss: 1.2851, Val Accuracy: 0.6205 Epoch 4149/10000, Train Loss: 1.2173, Train Accuracy: 0.6987, Val Loss: 1.2851, Val Accuracy: 0.6205 Epoch 4150/10000, Train Loss: 1.2067, Train Accuracy: 0.7188, Val Loss: 1.2849, Val Accuracy: 0.6205 Epoch 4151/10000, Train Loss: 1.2129, Train Accuracy: 0.7132, Val Loss: 1.2849, Val Accuracy: 0.6205 Epoch 4152/10000, Train Loss: 1.2068, Train Accuracy: 0.7143, Val Loss: 1.2850, Val Accuracy: 0.6205 Epoch 4153/10000, Train Loss: 1.2126, Train Accuracy: 0.7031, Val Loss: 1.2849, Val Accuracy: 0.6205 Epoch 4154/10000, Train Loss: 1.1981, Train Accuracy: 0.7243, Val Loss: 1.2848, Val Accuracy: 0.6205 Epoch 4155/10000, Train Loss: 1.2093, Train Accuracy: 0.7176, Val Loss: 1.2848, Val Accuracy: 0.6205 Epoch 4156/10000, Train Loss: 1.2171, Train Accuracy: 0.6953, Val Loss: 1.2848, Val Accuracy: 0.6205 Epoch 4157/10000, Train Loss: 1.2173, Train Accuracy: 0.7076, Val Loss: 1.2847, Val Accuracy: 0.6205 Epoch 4158/10000, Train Loss: 1.2156, Train Accuracy: 0.6998, Val Loss: 1.2846, Val Accuracy: 0.6205 Epoch 4159/10000, Train Loss: 1.2021, Train Accuracy: 0.7210, Val Loss: 1.2846, Val Accuracy: 0.6205 Epoch 4160/10000, Train Loss: 1.2188, Train Accuracy: 0.7042, Val Loss: 1.2846, Val Accuracy: 0.6205 Epoch 4161/10000, Train Loss: 1.1986, Train Accuracy: 0.7232, Val Loss: 1.2845, Val Accuracy: 0.6205 Epoch 4162/10000, Train Loss: 1.2147, Train Accuracy: 0.7042, Val Loss: 1.2844, Val Accuracy: 0.6205 Epoch 4163/10000, Train Loss: 1.2194, Train Accuracy: 0.6953, Val Loss: 1.2843, Val Accuracy: 0.6205 Epoch 4164/10000, Train Loss: 1.2051, Train Accuracy: 0.7087, Val Loss: 1.2843, Val Accuracy: 0.6205 Epoch 4165/10000, Train Loss: 1.2124, Train Accuracy: 0.7054, Val Loss: 1.2843, Val Accuracy: 0.6205 Epoch 4166/10000, Train Loss: 1.2159, Train Accuracy: 0.7054, Val Loss: 1.2841, Val Accuracy: 0.6205 Epoch 4167/10000, Train Loss: 1.2061, Train Accuracy: 0.7121, Val Loss: 1.2841, Val Accuracy: 0.6205 Epoch 4168/10000, Train Loss: 1.2118, Train Accuracy: 0.7121, Val Loss: 1.2840, Val Accuracy: 0.6205 Epoch 4169/10000, Train Loss: 1.2152, Train Accuracy: 0.7020, Val Loss: 1.2840, Val Accuracy: 0.6205 Epoch 4170/10000, Train Loss: 1.2191, Train Accuracy: 0.6875, Val Loss: 1.2840, Val Accuracy: 0.6205 Epoch 4171/10000, Train Loss: 1.2113, Train Accuracy: 0.7087, Val Loss: 1.2839, Val Accuracy: 0.6205 Epoch 4172/10000, Train Loss: 1.2035, Train Accuracy: 0.7277, Val Loss: 1.2838, Val Accuracy: 0.6205 Epoch 4173/10000, Train Loss: 1.2137, Train Accuracy: 0.7031, Val Loss: 1.2836, Val Accuracy: 0.6205 Epoch 4174/10000, Train Loss: 1.2172, Train Accuracy: 0.7121, Val Loss: 1.2836, Val Accuracy: 0.6205 Epoch 4175/10000, Train Loss: 1.2168, Train Accuracy: 0.7042, Val Loss: 1.2836, Val Accuracy: 0.6205 Epoch 4176/10000, Train Loss: 1.2111, Train Accuracy: 0.7132, Val Loss: 1.2836, Val Accuracy: 0.6205 Epoch 4177/10000, Train Loss: 1.2122, Train Accuracy: 0.7076, Val Loss: 1.2834, Val Accuracy: 0.6205 Epoch 4178/10000, Train Loss: 1.2171, Train Accuracy: 0.6998, Val Loss: 1.2833, Val Accuracy: 0.6205 Epoch 4179/10000, Train Loss: 1.2047, Train Accuracy: 0.7221, Val Loss: 1.2831, Val Accuracy: 0.6205 Epoch 4180/10000, Train Loss: 1.2048, Train Accuracy: 0.7132, Val Loss: 1.2832, Val Accuracy: 0.6205 Epoch 4181/10000, Train Loss: 1.2162, Train Accuracy: 0.6998, Val Loss: 1.2831, Val Accuracy: 0.6205 Epoch 4182/10000, Train Loss: 1.2144, Train Accuracy: 0.7042, Val Loss: 1.2831, Val Accuracy: 0.6205 Epoch 4183/10000, Train Loss: 1.2023, Train Accuracy: 0.7199, Val Loss: 1.2830, Val Accuracy: 0.6205 Epoch 4184/10000, Train Loss: 1.2003, Train Accuracy: 0.7165, Val Loss: 1.2830, Val Accuracy: 0.6205 Epoch 4185/10000, Train Loss: 1.2073, Train Accuracy: 0.7109, Val Loss: 1.2831, Val Accuracy: 0.6205 Epoch 4186/10000, Train Loss: 1.2130, Train Accuracy: 0.7031, Val Loss: 1.2830, Val Accuracy: 0.6205 Epoch 4187/10000, Train Loss: 1.2159, Train Accuracy: 0.7042, Val Loss: 1.2828, Val Accuracy: 0.6205 Epoch 4188/10000, Train Loss: 1.2046, Train Accuracy: 0.7210, Val Loss: 1.2827, Val Accuracy: 0.6205 Epoch 4189/10000, Train Loss: 1.2153, Train Accuracy: 0.7121, Val Loss: 1.2828, Val Accuracy: 0.6205 Epoch 4190/10000, Train Loss: 1.2139, Train Accuracy: 0.7087, Val Loss: 1.2828, Val Accuracy: 0.6205 Epoch 4191/10000, Train Loss: 1.2058, Train Accuracy: 0.7199, Val Loss: 1.2826, Val Accuracy: 0.6205 Epoch 4192/10000, Train Loss: 1.2012, Train Accuracy: 0.7299, Val Loss: 1.2824, Val Accuracy: 0.6205 Epoch 4193/10000, Train Loss: 1.2127, Train Accuracy: 0.7009, Val Loss: 1.2824, Val Accuracy: 0.6205 Epoch 4194/10000, Train Loss: 1.2053, Train Accuracy: 0.7154, Val Loss: 1.2823, Val Accuracy: 0.6205 Epoch 4195/10000, Train Loss: 1.2132, Train Accuracy: 0.7009, Val Loss: 1.2820, Val Accuracy: 0.6205 Epoch 4196/10000, Train Loss: 1.2083, Train Accuracy: 0.7121, Val Loss: 1.2821, Val Accuracy: 0.6205 Epoch 4197/10000, Train Loss: 1.2130, Train Accuracy: 0.7065, Val Loss: 1.2821, Val Accuracy: 0.6205 Epoch 4198/10000, Train Loss: 1.2168, Train Accuracy: 0.6975, Val Loss: 1.2820, Val Accuracy: 0.6205 Epoch 4199/10000, Train Loss: 1.2130, Train Accuracy: 0.7009, Val Loss: 1.2821, Val Accuracy: 0.6205 Epoch 4200/10000, Train Loss: 1.2117, Train Accuracy: 0.6975, Val Loss: 1.2821, Val Accuracy: 0.6205 Epoch 4201/10000, Train Loss: 1.2096, Train Accuracy: 0.7087, Val Loss: 1.2820, Val Accuracy: 0.6205 Epoch 4202/10000, Train Loss: 1.2040, Train Accuracy: 0.7165, Val Loss: 1.2821, Val Accuracy: 0.6205 Epoch 4203/10000, Train Loss: 1.2039, Train Accuracy: 0.7143, Val Loss: 1.2819, Val Accuracy: 0.6205 Epoch 4204/10000, Train Loss: 1.2099, Train Accuracy: 0.7054, Val Loss: 1.2820, Val Accuracy: 0.6205 Epoch 4205/10000, Train Loss: 1.2060, Train Accuracy: 0.7154, Val Loss: 1.2820, Val Accuracy: 0.6205 Epoch 4206/10000, Train Loss: 1.2024, Train Accuracy: 0.7221, Val Loss: 1.2819, Val Accuracy: 0.6205 Epoch 4207/10000, Train Loss: 1.2184, Train Accuracy: 0.6908, Val Loss: 1.2818, Val Accuracy: 0.6205 Epoch 4208/10000, Train Loss: 1.2020, Train Accuracy: 0.7109, Val Loss: 1.2817, Val Accuracy: 0.6205 Epoch 4209/10000, Train Loss: 1.2015, Train Accuracy: 0.7176, Val Loss: 1.2815, Val Accuracy: 0.6205 Epoch 4210/10000, Train Loss: 1.2185, Train Accuracy: 0.7087, Val Loss: 1.2815, Val Accuracy: 0.6205 Epoch 4211/10000, Train Loss: 1.2053, Train Accuracy: 0.7076, Val Loss: 1.2815, Val Accuracy: 0.6205 Epoch 4212/10000, Train Loss: 1.2059, Train Accuracy: 0.7154, Val Loss: 1.2814, Val Accuracy: 0.6205 Epoch 4213/10000, Train Loss: 1.2172, Train Accuracy: 0.6987, Val Loss: 1.2815, Val Accuracy: 0.6250 Epoch 4214/10000, Train Loss: 1.2113, Train Accuracy: 0.7165, Val Loss: 1.2811, Val Accuracy: 0.6250 Epoch 4215/10000, Train Loss: 1.2052, Train Accuracy: 0.7199, Val Loss: 1.2810, Val Accuracy: 0.6250 Epoch 4216/10000, Train Loss: 1.2027, Train Accuracy: 0.7143, Val Loss: 1.2809, Val Accuracy: 0.6250 Epoch 4217/10000, Train Loss: 1.2071, Train Accuracy: 0.7143, Val Loss: 1.2809, Val Accuracy: 0.6250 Epoch 4218/10000, Train Loss: 1.2000, Train Accuracy: 0.7266, Val Loss: 1.2808, Val Accuracy: 0.6250 Epoch 4219/10000, Train Loss: 1.2117, Train Accuracy: 0.7031, Val Loss: 1.2807, Val Accuracy: 0.6250 Epoch 4220/10000, Train Loss: 1.2103, Train Accuracy: 0.7054, Val Loss: 1.2807, Val Accuracy: 0.6250 Epoch 4221/10000, Train Loss: 1.2156, Train Accuracy: 0.7031, Val Loss: 1.2807, Val Accuracy: 0.6250 Epoch 4222/10000, Train Loss: 1.2083, Train Accuracy: 0.7109, Val Loss: 1.2808, Val Accuracy: 0.6250 Epoch 4223/10000, Train Loss: 1.2158, Train Accuracy: 0.6964, Val Loss: 1.2808, Val Accuracy: 0.6250 Epoch 4224/10000, Train Loss: 1.2077, Train Accuracy: 0.7165, Val Loss: 1.2808, Val Accuracy: 0.6250 Epoch 4225/10000, Train Loss: 1.2128, Train Accuracy: 0.7042, Val Loss: 1.2806, Val Accuracy: 0.6250 Epoch 4226/10000, Train Loss: 1.2030, Train Accuracy: 0.7188, Val Loss: 1.2804, Val Accuracy: 0.6250 Epoch 4227/10000, Train Loss: 1.1991, Train Accuracy: 0.7221, Val Loss: 1.2804, Val Accuracy: 0.6250 Epoch 4228/10000, Train Loss: 1.2118, Train Accuracy: 0.7143, Val Loss: 1.2804, Val Accuracy: 0.6250 Epoch 4229/10000, Train Loss: 1.1998, Train Accuracy: 0.7333, Val Loss: 1.2804, Val Accuracy: 0.6250 Epoch 4230/10000, Train Loss: 1.2012, Train Accuracy: 0.7154, Val Loss: 1.2802, Val Accuracy: 0.6250 Epoch 4231/10000, Train Loss: 1.1995, Train Accuracy: 0.7277, Val Loss: 1.2801, Val Accuracy: 0.6250 Epoch 4232/10000, Train Loss: 1.2066, Train Accuracy: 0.7087, Val Loss: 1.2803, Val Accuracy: 0.6250 Epoch 4233/10000, Train Loss: 1.2079, Train Accuracy: 0.7132, Val Loss: 1.2802, Val Accuracy: 0.6250 Epoch 4234/10000, Train Loss: 1.2073, Train Accuracy: 0.7221, Val Loss: 1.2802, Val Accuracy: 0.6250 Epoch 4235/10000, Train Loss: 1.2053, Train Accuracy: 0.7098, Val Loss: 1.2803, Val Accuracy: 0.6250 Epoch 4236/10000, Train Loss: 1.2084, Train Accuracy: 0.7065, Val Loss: 1.2803, Val Accuracy: 0.6250 Epoch 4237/10000, Train Loss: 1.2020, Train Accuracy: 0.7210, Val Loss: 1.2801, Val Accuracy: 0.6250 Epoch 4238/10000, Train Loss: 1.2109, Train Accuracy: 0.7132, Val Loss: 1.2800, Val Accuracy: 0.6250 Epoch 4239/10000, Train Loss: 1.2178, Train Accuracy: 0.7087, Val Loss: 1.2800, Val Accuracy: 0.6250 Epoch 4240/10000, Train Loss: 1.2025, Train Accuracy: 0.7165, Val Loss: 1.2800, Val Accuracy: 0.6250 Epoch 4241/10000, Train Loss: 1.2110, Train Accuracy: 0.6920, Val Loss: 1.2799, Val Accuracy: 0.6250 Epoch 4242/10000, Train Loss: 1.2100, Train Accuracy: 0.6998, Val Loss: 1.2798, Val Accuracy: 0.6250 Epoch 4243/10000, Train Loss: 1.2071, Train Accuracy: 0.7109, Val Loss: 1.2797, Val Accuracy: 0.6250 Epoch 4244/10000, Train Loss: 1.2007, Train Accuracy: 0.7176, Val Loss: 1.2796, Val Accuracy: 0.6250 Epoch 4245/10000, Train Loss: 1.2058, Train Accuracy: 0.7076, Val Loss: 1.2796, Val Accuracy: 0.6250 Epoch 4246/10000, Train Loss: 1.2098, Train Accuracy: 0.7176, Val Loss: 1.2795, Val Accuracy: 0.6250 Epoch 4247/10000, Train Loss: 1.2045, Train Accuracy: 0.7165, Val Loss: 1.2794, Val Accuracy: 0.6250 Epoch 4248/10000, Train Loss: 1.2115, Train Accuracy: 0.7076, Val Loss: 1.2793, Val Accuracy: 0.6250 Epoch 4249/10000, Train Loss: 1.2163, Train Accuracy: 0.7042, Val Loss: 1.2791, Val Accuracy: 0.6250 Epoch 4250/10000, Train Loss: 1.2068, Train Accuracy: 0.7109, Val Loss: 1.2790, Val Accuracy: 0.6250 Epoch 4251/10000, Train Loss: 1.2003, Train Accuracy: 0.7321, Val Loss: 1.2789, Val Accuracy: 0.6250 Epoch 4252/10000, Train Loss: 1.2054, Train Accuracy: 0.7109, Val Loss: 1.2790, Val Accuracy: 0.6250 Epoch 4253/10000, Train Loss: 1.2046, Train Accuracy: 0.7087, Val Loss: 1.2789, Val Accuracy: 0.6250 Epoch 4254/10000, Train Loss: 1.2167, Train Accuracy: 0.6975, Val Loss: 1.2788, Val Accuracy: 0.6250 Epoch 4255/10000, Train Loss: 1.1991, Train Accuracy: 0.7243, Val Loss: 1.2789, Val Accuracy: 0.6250 Epoch 4256/10000, Train Loss: 1.2075, Train Accuracy: 0.7076, Val Loss: 1.2788, Val Accuracy: 0.6250 Epoch 4257/10000, Train Loss: 1.2142, Train Accuracy: 0.7109, Val Loss: 1.2787, Val Accuracy: 0.6250 Epoch 4258/10000, Train Loss: 1.2071, Train Accuracy: 0.7121, Val Loss: 1.2786, Val Accuracy: 0.6250 Epoch 4259/10000, Train Loss: 1.2032, Train Accuracy: 0.7277, Val Loss: 1.2785, Val Accuracy: 0.6250 Epoch 4260/10000, Train Loss: 1.2045, Train Accuracy: 0.7176, Val Loss: 1.2784, Val Accuracy: 0.6250 Epoch 4261/10000, Train Loss: 1.2093, Train Accuracy: 0.7176, Val Loss: 1.2784, Val Accuracy: 0.6250 Epoch 4262/10000, Train Loss: 1.1999, Train Accuracy: 0.7143, Val Loss: 1.2783, Val Accuracy: 0.6250 Epoch 4263/10000, Train Loss: 1.2099, Train Accuracy: 0.7143, Val Loss: 1.2784, Val Accuracy: 0.6250 Epoch 4264/10000, Train Loss: 1.1991, Train Accuracy: 0.7221, Val Loss: 1.2785, Val Accuracy: 0.6250 Epoch 4265/10000, Train Loss: 1.1952, Train Accuracy: 0.7299, Val Loss: 1.2785, Val Accuracy: 0.6250 Epoch 4266/10000, Train Loss: 1.1892, Train Accuracy: 0.7288, Val Loss: 1.2784, Val Accuracy: 0.6250 Epoch 4267/10000, Train Loss: 1.1929, Train Accuracy: 0.7310, Val Loss: 1.2783, Val Accuracy: 0.6250 Epoch 4268/10000, Train Loss: 1.2050, Train Accuracy: 0.7109, Val Loss: 1.2784, Val Accuracy: 0.6250 Epoch 4269/10000, Train Loss: 1.2048, Train Accuracy: 0.7254, Val Loss: 1.2783, Val Accuracy: 0.6250 Epoch 4270/10000, Train Loss: 1.2015, Train Accuracy: 0.7087, Val Loss: 1.2782, Val Accuracy: 0.6250 Epoch 4271/10000, Train Loss: 1.1962, Train Accuracy: 0.7232, Val Loss: 1.2781, Val Accuracy: 0.6250 Epoch 4272/10000, Train Loss: 1.2144, Train Accuracy: 0.6998, Val Loss: 1.2781, Val Accuracy: 0.6250 Epoch 4273/10000, Train Loss: 1.2021, Train Accuracy: 0.7176, Val Loss: 1.2780, Val Accuracy: 0.6250 Epoch 4274/10000, Train Loss: 1.2111, Train Accuracy: 0.7009, Val Loss: 1.2779, Val Accuracy: 0.6250 Epoch 4275/10000, Train Loss: 1.2018, Train Accuracy: 0.7165, Val Loss: 1.2779, Val Accuracy: 0.6250 Epoch 4276/10000, Train Loss: 1.2065, Train Accuracy: 0.7199, Val Loss: 1.2778, Val Accuracy: 0.6250 Epoch 4277/10000, Train Loss: 1.2041, Train Accuracy: 0.7176, Val Loss: 1.2777, Val Accuracy: 0.6250 Epoch 4278/10000, Train Loss: 1.1997, Train Accuracy: 0.7254, Val Loss: 1.2776, Val Accuracy: 0.6250 Epoch 4279/10000, Train Loss: 1.2038, Train Accuracy: 0.7221, Val Loss: 1.2776, Val Accuracy: 0.6250 Epoch 4280/10000, Train Loss: 1.2138, Train Accuracy: 0.6975, Val Loss: 1.2776, Val Accuracy: 0.6250 Epoch 4281/10000, Train Loss: 1.2130, Train Accuracy: 0.7054, Val Loss: 1.2776, Val Accuracy: 0.6250 Epoch 4282/10000, Train Loss: 1.1928, Train Accuracy: 0.7355, Val Loss: 1.2774, Val Accuracy: 0.6250 Epoch 4283/10000, Train Loss: 1.2112, Train Accuracy: 0.7087, Val Loss: 1.2774, Val Accuracy: 0.6250 Epoch 4284/10000, Train Loss: 1.1995, Train Accuracy: 0.7199, Val Loss: 1.2774, Val Accuracy: 0.6250 Epoch 4285/10000, Train Loss: 1.1940, Train Accuracy: 0.7388, Val Loss: 1.2773, Val Accuracy: 0.6250 Epoch 4286/10000, Train Loss: 1.2063, Train Accuracy: 0.7165, Val Loss: 1.2774, Val Accuracy: 0.6250 Epoch 4287/10000, Train Loss: 1.1931, Train Accuracy: 0.7277, Val Loss: 1.2774, Val Accuracy: 0.6250 Epoch 4288/10000, Train Loss: 1.2002, Train Accuracy: 0.7109, Val Loss: 1.2774, Val Accuracy: 0.6250 Epoch 4289/10000, Train Loss: 1.2095, Train Accuracy: 0.7042, Val Loss: 1.2772, Val Accuracy: 0.6250 Epoch 4290/10000, Train Loss: 1.1963, Train Accuracy: 0.7165, Val Loss: 1.2772, Val Accuracy: 0.6250 Epoch 4291/10000, Train Loss: 1.2063, Train Accuracy: 0.7076, Val Loss: 1.2770, Val Accuracy: 0.6250 Epoch 4292/10000, Train Loss: 1.2080, Train Accuracy: 0.7188, Val Loss: 1.2771, Val Accuracy: 0.6250 Epoch 4293/10000, Train Loss: 1.1995, Train Accuracy: 0.7188, Val Loss: 1.2769, Val Accuracy: 0.6250 Epoch 4294/10000, Train Loss: 1.1970, Train Accuracy: 0.7210, Val Loss: 1.2768, Val Accuracy: 0.6250 Epoch 4295/10000, Train Loss: 1.1975, Train Accuracy: 0.7333, Val Loss: 1.2768, Val Accuracy: 0.6250 Epoch 4296/10000, Train Loss: 1.2131, Train Accuracy: 0.6975, Val Loss: 1.2767, Val Accuracy: 0.6250 Epoch 4297/10000, Train Loss: 1.1946, Train Accuracy: 0.7266, Val Loss: 1.2767, Val Accuracy: 0.6250 Epoch 4298/10000, Train Loss: 1.2014, Train Accuracy: 0.7143, Val Loss: 1.2767, Val Accuracy: 0.6250 Epoch 4299/10000, Train Loss: 1.1893, Train Accuracy: 0.7277, Val Loss: 1.2767, Val Accuracy: 0.6250 Epoch 4300/10000, Train Loss: 1.2079, Train Accuracy: 0.7098, Val Loss: 1.2765, Val Accuracy: 0.6250 Epoch 4301/10000, Train Loss: 1.2195, Train Accuracy: 0.6942, Val Loss: 1.2765, Val Accuracy: 0.6250 Epoch 4302/10000, Train Loss: 1.2088, Train Accuracy: 0.7109, Val Loss: 1.2766, Val Accuracy: 0.6250 Epoch 4303/10000, Train Loss: 1.1898, Train Accuracy: 0.7254, Val Loss: 1.2766, Val Accuracy: 0.6250 Epoch 4304/10000, Train Loss: 1.2087, Train Accuracy: 0.7109, Val Loss: 1.2765, Val Accuracy: 0.6250 Epoch 4305/10000, Train Loss: 1.1954, Train Accuracy: 0.7232, Val Loss: 1.2764, Val Accuracy: 0.6250 Epoch 4306/10000, Train Loss: 1.1974, Train Accuracy: 0.7288, Val Loss: 1.2764, Val Accuracy: 0.6250 Epoch 4307/10000, Train Loss: 1.2002, Train Accuracy: 0.7221, Val Loss: 1.2764, Val Accuracy: 0.6295 Epoch 4308/10000, Train Loss: 1.1899, Train Accuracy: 0.7333, Val Loss: 1.2765, Val Accuracy: 0.6295 Epoch 4309/10000, Train Loss: 1.1952, Train Accuracy: 0.7232, Val Loss: 1.2765, Val Accuracy: 0.6295 Epoch 4310/10000, Train Loss: 1.2064, Train Accuracy: 0.7143, Val Loss: 1.2764, Val Accuracy: 0.6250 Epoch 4311/10000, Train Loss: 1.2010, Train Accuracy: 0.7232, Val Loss: 1.2763, Val Accuracy: 0.6250 Epoch 4312/10000, Train Loss: 1.2087, Train Accuracy: 0.7065, Val Loss: 1.2762, Val Accuracy: 0.6250 Epoch 4313/10000, Train Loss: 1.1935, Train Accuracy: 0.7188, Val Loss: 1.2762, Val Accuracy: 0.6295 Epoch 4314/10000, Train Loss: 1.1948, Train Accuracy: 0.7277, Val Loss: 1.2762, Val Accuracy: 0.6295 Epoch 4315/10000, Train Loss: 1.1917, Train Accuracy: 0.7288, Val Loss: 1.2761, Val Accuracy: 0.6250 Epoch 4316/10000, Train Loss: 1.2004, Train Accuracy: 0.7210, Val Loss: 1.2761, Val Accuracy: 0.6295 Epoch 4317/10000, Train Loss: 1.2084, Train Accuracy: 0.7098, Val Loss: 1.2760, Val Accuracy: 0.6295 Epoch 4318/10000, Train Loss: 1.1933, Train Accuracy: 0.7277, Val Loss: 1.2761, Val Accuracy: 0.6295 Epoch 4319/10000, Train Loss: 1.2006, Train Accuracy: 0.7143, Val Loss: 1.2760, Val Accuracy: 0.6295 Epoch 4320/10000, Train Loss: 1.1926, Train Accuracy: 0.7321, Val Loss: 1.2758, Val Accuracy: 0.6295 Epoch 4321/10000, Train Loss: 1.1961, Train Accuracy: 0.7243, Val Loss: 1.2757, Val Accuracy: 0.6295 Epoch 4322/10000, Train Loss: 1.1964, Train Accuracy: 0.7243, Val Loss: 1.2756, Val Accuracy: 0.6295 Epoch 4323/10000, Train Loss: 1.2015, Train Accuracy: 0.7165, Val Loss: 1.2755, Val Accuracy: 0.6295 Epoch 4324/10000, Train Loss: 1.2006, Train Accuracy: 0.7266, Val Loss: 1.2755, Val Accuracy: 0.6295 Epoch 4325/10000, Train Loss: 1.1993, Train Accuracy: 0.7232, Val Loss: 1.2755, Val Accuracy: 0.6295 Epoch 4326/10000, Train Loss: 1.2049, Train Accuracy: 0.7188, Val Loss: 1.2755, Val Accuracy: 0.6295 Epoch 4327/10000, Train Loss: 1.1924, Train Accuracy: 0.7199, Val Loss: 1.2753, Val Accuracy: 0.6295 Epoch 4328/10000, Train Loss: 1.2065, Train Accuracy: 0.6987, Val Loss: 1.2753, Val Accuracy: 0.6295 Epoch 4329/10000, Train Loss: 1.2075, Train Accuracy: 0.7165, Val Loss: 1.2754, Val Accuracy: 0.6295 Epoch 4330/10000, Train Loss: 1.2085, Train Accuracy: 0.7121, Val Loss: 1.2754, Val Accuracy: 0.6295 Epoch 4331/10000, Train Loss: 1.1992, Train Accuracy: 0.7154, Val Loss: 1.2752, Val Accuracy: 0.6295 Epoch 4332/10000, Train Loss: 1.1968, Train Accuracy: 0.7109, Val Loss: 1.2753, Val Accuracy: 0.6295 Epoch 4333/10000, Train Loss: 1.1982, Train Accuracy: 0.7288, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4334/10000, Train Loss: 1.1906, Train Accuracy: 0.7411, Val Loss: 1.2752, Val Accuracy: 0.6295 Epoch 4335/10000, Train Loss: 1.1962, Train Accuracy: 0.7321, Val Loss: 1.2750, Val Accuracy: 0.6295 Epoch 4336/10000, Train Loss: 1.2068, Train Accuracy: 0.7154, Val Loss: 1.2749, Val Accuracy: 0.6295 Epoch 4337/10000, Train Loss: 1.1963, Train Accuracy: 0.7243, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4338/10000, Train Loss: 1.2041, Train Accuracy: 0.7143, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4339/10000, Train Loss: 1.1875, Train Accuracy: 0.7400, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4340/10000, Train Loss: 1.2051, Train Accuracy: 0.7165, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4341/10000, Train Loss: 1.2004, Train Accuracy: 0.7266, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4342/10000, Train Loss: 1.1936, Train Accuracy: 0.7388, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4343/10000, Train Loss: 1.2022, Train Accuracy: 0.7210, Val Loss: 1.2752, Val Accuracy: 0.6295 Epoch 4344/10000, Train Loss: 1.1944, Train Accuracy: 0.7288, Val Loss: 1.2752, Val Accuracy: 0.6295 Epoch 4345/10000, Train Loss: 1.2054, Train Accuracy: 0.7243, Val Loss: 1.2751, Val Accuracy: 0.6295 Epoch 4346/10000, Train Loss: 1.2089, Train Accuracy: 0.7098, Val Loss: 1.2749, Val Accuracy: 0.6295 Epoch 4347/10000, Train Loss: 1.2027, Train Accuracy: 0.7165, Val Loss: 1.2749, Val Accuracy: 0.6295 Epoch 4348/10000, Train Loss: 1.2133, Train Accuracy: 0.6998, Val Loss: 1.2748, Val Accuracy: 0.6295 Epoch 4349/10000, Train Loss: 1.1894, Train Accuracy: 0.7310, Val Loss: 1.2748, Val Accuracy: 0.6295 Epoch 4350/10000, Train Loss: 1.1985, Train Accuracy: 0.7254, Val Loss: 1.2747, Val Accuracy: 0.6295 Epoch 4351/10000, Train Loss: 1.2047, Train Accuracy: 0.7176, Val Loss: 1.2746, Val Accuracy: 0.6295 Epoch 4352/10000, Train Loss: 1.1961, Train Accuracy: 0.7210, Val Loss: 1.2746, Val Accuracy: 0.6295 Epoch 4353/10000, Train Loss: 1.1930, Train Accuracy: 0.7310, Val Loss: 1.2744, Val Accuracy: 0.6295 Epoch 4354/10000, Train Loss: 1.1970, Train Accuracy: 0.7232, Val Loss: 1.2744, Val Accuracy: 0.6295 Epoch 4355/10000, Train Loss: 1.1983, Train Accuracy: 0.7243, Val Loss: 1.2743, Val Accuracy: 0.6295 Epoch 4356/10000, Train Loss: 1.2013, Train Accuracy: 0.7266, Val Loss: 1.2742, Val Accuracy: 0.6295 Epoch 4357/10000, Train Loss: 1.1968, Train Accuracy: 0.7199, Val Loss: 1.2742, Val Accuracy: 0.6295 Epoch 4358/10000, Train Loss: 1.2081, Train Accuracy: 0.7042, Val Loss: 1.2741, Val Accuracy: 0.6295 Epoch 4359/10000, Train Loss: 1.1934, Train Accuracy: 0.7254, Val Loss: 1.2741, Val Accuracy: 0.6295 Epoch 4360/10000, Train Loss: 1.1983, Train Accuracy: 0.7210, Val Loss: 1.2742, Val Accuracy: 0.6295 Epoch 4361/10000, Train Loss: 1.1995, Train Accuracy: 0.7199, Val Loss: 1.2741, Val Accuracy: 0.6250 Epoch 4362/10000, Train Loss: 1.1946, Train Accuracy: 0.7288, Val Loss: 1.2740, Val Accuracy: 0.6295 Epoch 4363/10000, Train Loss: 1.1981, Train Accuracy: 0.7277, Val Loss: 1.2740, Val Accuracy: 0.6295 Epoch 4364/10000, Train Loss: 1.1955, Train Accuracy: 0.7221, Val Loss: 1.2739, Val Accuracy: 0.6295 Epoch 4365/10000, Train Loss: 1.2009, Train Accuracy: 0.7143, Val Loss: 1.2739, Val Accuracy: 0.6295 Epoch 4366/10000, Train Loss: 1.1953, Train Accuracy: 0.7254, Val Loss: 1.2738, Val Accuracy: 0.6295 Epoch 4367/10000, Train Loss: 1.2031, Train Accuracy: 0.7076, Val Loss: 1.2736, Val Accuracy: 0.6295 Epoch 4368/10000, Train Loss: 1.2036, Train Accuracy: 0.7121, Val Loss: 1.2736, Val Accuracy: 0.6295 Epoch 4369/10000, Train Loss: 1.1976, Train Accuracy: 0.7165, Val Loss: 1.2736, Val Accuracy: 0.6295 Epoch 4370/10000, Train Loss: 1.1827, Train Accuracy: 0.7533, Val Loss: 1.2735, Val Accuracy: 0.6295 Epoch 4371/10000, Train Loss: 1.1896, Train Accuracy: 0.7254, Val Loss: 1.2735, Val Accuracy: 0.6295 Epoch 4372/10000, Train Loss: 1.2021, Train Accuracy: 0.7232, Val Loss: 1.2732, Val Accuracy: 0.6295 Epoch 4373/10000, Train Loss: 1.2051, Train Accuracy: 0.7165, Val Loss: 1.2732, Val Accuracy: 0.6295 Epoch 4374/10000, Train Loss: 1.2077, Train Accuracy: 0.7065, Val Loss: 1.2731, Val Accuracy: 0.6295 Epoch 4375/10000, Train Loss: 1.2009, Train Accuracy: 0.7188, Val Loss: 1.2730, Val Accuracy: 0.6295 Epoch 4376/10000, Train Loss: 1.2001, Train Accuracy: 0.7243, Val Loss: 1.2730, Val Accuracy: 0.6295 Epoch 4377/10000, Train Loss: 1.1987, Train Accuracy: 0.7143, Val Loss: 1.2728, Val Accuracy: 0.6295 Epoch 4378/10000, Train Loss: 1.2066, Train Accuracy: 0.7087, Val Loss: 1.2727, Val Accuracy: 0.6295 Epoch 4379/10000, Train Loss: 1.2056, Train Accuracy: 0.7087, Val Loss: 1.2728, Val Accuracy: 0.6250 Epoch 4380/10000, Train Loss: 1.2032, Train Accuracy: 0.7087, Val Loss: 1.2729, Val Accuracy: 0.6295 Epoch 4381/10000, Train Loss: 1.2014, Train Accuracy: 0.7154, Val Loss: 1.2728, Val Accuracy: 0.6295 Epoch 4382/10000, Train Loss: 1.1881, Train Accuracy: 0.7333, Val Loss: 1.2728, Val Accuracy: 0.6295 Epoch 4383/10000, Train Loss: 1.2015, Train Accuracy: 0.7221, Val Loss: 1.2728, Val Accuracy: 0.6295 Epoch 4384/10000, Train Loss: 1.1911, Train Accuracy: 0.7288, Val Loss: 1.2728, Val Accuracy: 0.6295 Epoch 4385/10000, Train Loss: 1.1974, Train Accuracy: 0.7321, Val Loss: 1.2727, Val Accuracy: 0.6295 Epoch 4386/10000, Train Loss: 1.1976, Train Accuracy: 0.7176, Val Loss: 1.2726, Val Accuracy: 0.6295 Epoch 4387/10000, Train Loss: 1.2035, Train Accuracy: 0.7121, Val Loss: 1.2727, Val Accuracy: 0.6295 Epoch 4388/10000, Train Loss: 1.1985, Train Accuracy: 0.7277, Val Loss: 1.2726, Val Accuracy: 0.6250 Epoch 4389/10000, Train Loss: 1.1924, Train Accuracy: 0.7344, Val Loss: 1.2725, Val Accuracy: 0.6250 Epoch 4390/10000, Train Loss: 1.2084, Train Accuracy: 0.7121, Val Loss: 1.2725, Val Accuracy: 0.6250 Epoch 4391/10000, Train Loss: 1.1994, Train Accuracy: 0.7165, Val Loss: 1.2723, Val Accuracy: 0.6250 Epoch 4392/10000, Train Loss: 1.2043, Train Accuracy: 0.7098, Val Loss: 1.2724, Val Accuracy: 0.6250 Epoch 4393/10000, Train Loss: 1.1930, Train Accuracy: 0.7377, Val Loss: 1.2724, Val Accuracy: 0.6250 Epoch 4394/10000, Train Loss: 1.1927, Train Accuracy: 0.7310, Val Loss: 1.2722, Val Accuracy: 0.6339 Epoch 4395/10000, Train Loss: 1.1941, Train Accuracy: 0.7188, Val Loss: 1.2723, Val Accuracy: 0.6295 Epoch 4396/10000, Train Loss: 1.2016, Train Accuracy: 0.7154, Val Loss: 1.2721, Val Accuracy: 0.6295 Epoch 4397/10000, Train Loss: 1.1972, Train Accuracy: 0.7154, Val Loss: 1.2721, Val Accuracy: 0.6295 Epoch 4398/10000, Train Loss: 1.1974, Train Accuracy: 0.7232, Val Loss: 1.2721, Val Accuracy: 0.6295 Epoch 4399/10000, Train Loss: 1.1970, Train Accuracy: 0.7176, Val Loss: 1.2720, Val Accuracy: 0.6295 Epoch 4400/10000, Train Loss: 1.1959, Train Accuracy: 0.7266, Val Loss: 1.2720, Val Accuracy: 0.6295 Epoch 4401/10000, Train Loss: 1.2041, Train Accuracy: 0.7266, Val Loss: 1.2717, Val Accuracy: 0.6295 Epoch 4402/10000, Train Loss: 1.2079, Train Accuracy: 0.7065, Val Loss: 1.2715, Val Accuracy: 0.6295 Epoch 4403/10000, Train Loss: 1.1883, Train Accuracy: 0.7310, Val Loss: 1.2714, Val Accuracy: 0.6295 Epoch 4404/10000, Train Loss: 1.1972, Train Accuracy: 0.7154, Val Loss: 1.2713, Val Accuracy: 0.6295 Epoch 4405/10000, Train Loss: 1.1957, Train Accuracy: 0.7121, Val Loss: 1.2712, Val Accuracy: 0.6295 Epoch 4406/10000, Train Loss: 1.1914, Train Accuracy: 0.7333, Val Loss: 1.2711, Val Accuracy: 0.6295 Epoch 4407/10000, Train Loss: 1.1847, Train Accuracy: 0.7444, Val Loss: 1.2711, Val Accuracy: 0.6295 Epoch 4408/10000, Train Loss: 1.1991, Train Accuracy: 0.7210, Val Loss: 1.2709, Val Accuracy: 0.6295 Epoch 4409/10000, Train Loss: 1.1888, Train Accuracy: 0.7221, Val Loss: 1.2709, Val Accuracy: 0.6339 Epoch 4410/10000, Train Loss: 1.1888, Train Accuracy: 0.7321, Val Loss: 1.2709, Val Accuracy: 0.6295 Epoch 4411/10000, Train Loss: 1.1902, Train Accuracy: 0.7310, Val Loss: 1.2710, Val Accuracy: 0.6295 Epoch 4412/10000, Train Loss: 1.1924, Train Accuracy: 0.7266, Val Loss: 1.2711, Val Accuracy: 0.6295 Epoch 4413/10000, Train Loss: 1.1899, Train Accuracy: 0.7243, Val Loss: 1.2710, Val Accuracy: 0.6295 Epoch 4414/10000, Train Loss: 1.1915, Train Accuracy: 0.7400, Val Loss: 1.2709, Val Accuracy: 0.6295 Epoch 4415/10000, Train Loss: 1.2008, Train Accuracy: 0.7188, Val Loss: 1.2709, Val Accuracy: 0.6295 Epoch 4416/10000, Train Loss: 1.2025, Train Accuracy: 0.7199, Val Loss: 1.2709, Val Accuracy: 0.6295 Epoch 4417/10000, Train Loss: 1.1946, Train Accuracy: 0.7277, Val Loss: 1.2708, Val Accuracy: 0.6295 Epoch 4418/10000, Train Loss: 1.1957, Train Accuracy: 0.7266, Val Loss: 1.2708, Val Accuracy: 0.6295 Epoch 4419/10000, Train Loss: 1.1932, Train Accuracy: 0.7199, Val Loss: 1.2706, Val Accuracy: 0.6295 Epoch 4420/10000, Train Loss: 1.1974, Train Accuracy: 0.7176, Val Loss: 1.2706, Val Accuracy: 0.6295 Epoch 4421/10000, Train Loss: 1.1997, Train Accuracy: 0.7154, Val Loss: 1.2706, Val Accuracy: 0.6295 Epoch 4422/10000, Train Loss: 1.1835, Train Accuracy: 0.7344, Val Loss: 1.2706, Val Accuracy: 0.6295 Epoch 4423/10000, Train Loss: 1.1962, Train Accuracy: 0.7121, Val Loss: 1.2705, Val Accuracy: 0.6295 Epoch 4424/10000, Train Loss: 1.1977, Train Accuracy: 0.7321, Val Loss: 1.2703, Val Accuracy: 0.6295 Epoch 4425/10000, Train Loss: 1.1944, Train Accuracy: 0.7221, Val Loss: 1.2703, Val Accuracy: 0.6295 Epoch 4426/10000, Train Loss: 1.1918, Train Accuracy: 0.7277, Val Loss: 1.2702, Val Accuracy: 0.6295 Epoch 4427/10000, Train Loss: 1.1925, Train Accuracy: 0.7221, Val Loss: 1.2700, Val Accuracy: 0.6295 Epoch 4428/10000, Train Loss: 1.1918, Train Accuracy: 0.7232, Val Loss: 1.2700, Val Accuracy: 0.6339 Epoch 4429/10000, Train Loss: 1.1869, Train Accuracy: 0.7266, Val Loss: 1.2699, Val Accuracy: 0.6295 Epoch 4430/10000, Train Loss: 1.1893, Train Accuracy: 0.7366, Val Loss: 1.2698, Val Accuracy: 0.6295 Epoch 4431/10000, Train Loss: 1.1937, Train Accuracy: 0.7176, Val Loss: 1.2698, Val Accuracy: 0.6339 Epoch 4432/10000, Train Loss: 1.2102, Train Accuracy: 0.6998, Val Loss: 1.2697, Val Accuracy: 0.6339 Epoch 4433/10000, Train Loss: 1.1857, Train Accuracy: 0.7388, Val Loss: 1.2697, Val Accuracy: 0.6339 Epoch 4434/10000, Train Loss: 1.1998, Train Accuracy: 0.7109, Val Loss: 1.2695, Val Accuracy: 0.6339 Epoch 4435/10000, Train Loss: 1.1944, Train Accuracy: 0.7266, Val Loss: 1.2695, Val Accuracy: 0.6295 Epoch 4436/10000, Train Loss: 1.1850, Train Accuracy: 0.7455, Val Loss: 1.2695, Val Accuracy: 0.6295 Epoch 4437/10000, Train Loss: 1.2002, Train Accuracy: 0.7109, Val Loss: 1.2694, Val Accuracy: 0.6295 Epoch 4438/10000, Train Loss: 1.2134, Train Accuracy: 0.7020, Val Loss: 1.2694, Val Accuracy: 0.6295 Epoch 4439/10000, Train Loss: 1.1938, Train Accuracy: 0.7299, Val Loss: 1.2692, Val Accuracy: 0.6339 Epoch 4440/10000, Train Loss: 1.1987, Train Accuracy: 0.7221, Val Loss: 1.2692, Val Accuracy: 0.6339 Epoch 4441/10000, Train Loss: 1.1907, Train Accuracy: 0.7288, Val Loss: 1.2692, Val Accuracy: 0.6339 Epoch 4442/10000, Train Loss: 1.1971, Train Accuracy: 0.7210, Val Loss: 1.2693, Val Accuracy: 0.6295 Epoch 4443/10000, Train Loss: 1.1779, Train Accuracy: 0.7400, Val Loss: 1.2694, Val Accuracy: 0.6295 Epoch 4444/10000, Train Loss: 1.2098, Train Accuracy: 0.7109, Val Loss: 1.2694, Val Accuracy: 0.6295 Epoch 4445/10000, Train Loss: 1.1987, Train Accuracy: 0.7254, Val Loss: 1.2693, Val Accuracy: 0.6295 Epoch 4446/10000, Train Loss: 1.2037, Train Accuracy: 0.7176, Val Loss: 1.2693, Val Accuracy: 0.6295 Epoch 4447/10000, Train Loss: 1.1964, Train Accuracy: 0.7299, Val Loss: 1.2691, Val Accuracy: 0.6339 Epoch 4448/10000, Train Loss: 1.1869, Train Accuracy: 0.7344, Val Loss: 1.2690, Val Accuracy: 0.6339 Epoch 4449/10000, Train Loss: 1.1839, Train Accuracy: 0.7366, Val Loss: 1.2690, Val Accuracy: 0.6339 Epoch 4450/10000, Train Loss: 1.1997, Train Accuracy: 0.7221, Val Loss: 1.2688, Val Accuracy: 0.6339 Epoch 4451/10000, Train Loss: 1.2036, Train Accuracy: 0.7109, Val Loss: 1.2687, Val Accuracy: 0.6339 Epoch 4452/10000, Train Loss: 1.1977, Train Accuracy: 0.7210, Val Loss: 1.2687, Val Accuracy: 0.6339 Epoch 4453/10000, Train Loss: 1.2004, Train Accuracy: 0.7176, Val Loss: 1.2686, Val Accuracy: 0.6384 Epoch 4454/10000, Train Loss: 1.1884, Train Accuracy: 0.7333, Val Loss: 1.2686, Val Accuracy: 0.6384 Epoch 4455/10000, Train Loss: 1.1911, Train Accuracy: 0.7254, Val Loss: 1.2685, Val Accuracy: 0.6429 Epoch 4456/10000, Train Loss: 1.1780, Train Accuracy: 0.7444, Val Loss: 1.2685, Val Accuracy: 0.6339 Epoch 4457/10000, Train Loss: 1.2067, Train Accuracy: 0.7020, Val Loss: 1.2686, Val Accuracy: 0.6339 Epoch 4458/10000, Train Loss: 1.2081, Train Accuracy: 0.7076, Val Loss: 1.2686, Val Accuracy: 0.6339 Epoch 4459/10000, Train Loss: 1.1944, Train Accuracy: 0.7310, Val Loss: 1.2685, Val Accuracy: 0.6384 Epoch 4460/10000, Train Loss: 1.1896, Train Accuracy: 0.7199, Val Loss: 1.2686, Val Accuracy: 0.6295 Epoch 4461/10000, Train Loss: 1.1913, Train Accuracy: 0.7243, Val Loss: 1.2687, Val Accuracy: 0.6384 Epoch 4462/10000, Train Loss: 1.1978, Train Accuracy: 0.7277, Val Loss: 1.2686, Val Accuracy: 0.6339 Epoch 4463/10000, Train Loss: 1.1883, Train Accuracy: 0.7310, Val Loss: 1.2686, Val Accuracy: 0.6339 Epoch 4464/10000, Train Loss: 1.1942, Train Accuracy: 0.7221, Val Loss: 1.2686, Val Accuracy: 0.6339 Epoch 4465/10000, Train Loss: 1.1883, Train Accuracy: 0.7310, Val Loss: 1.2685, Val Accuracy: 0.6339 Epoch 4466/10000, Train Loss: 1.1923, Train Accuracy: 0.7344, Val Loss: 1.2684, Val Accuracy: 0.6339 Epoch 4467/10000, Train Loss: 1.1878, Train Accuracy: 0.7321, Val Loss: 1.2684, Val Accuracy: 0.6339 Epoch 4468/10000, Train Loss: 1.1724, Train Accuracy: 0.7567, Val Loss: 1.2684, Val Accuracy: 0.6339 Epoch 4469/10000, Train Loss: 1.1921, Train Accuracy: 0.7310, Val Loss: 1.2682, Val Accuracy: 0.6339 Epoch 4470/10000, Train Loss: 1.2003, Train Accuracy: 0.7143, Val Loss: 1.2682, Val Accuracy: 0.6339 Epoch 4471/10000, Train Loss: 1.1989, Train Accuracy: 0.7221, Val Loss: 1.2683, Val Accuracy: 0.6339 Epoch 4472/10000, Train Loss: 1.1989, Train Accuracy: 0.7176, Val Loss: 1.2683, Val Accuracy: 0.6339 Epoch 4473/10000, Train Loss: 1.1919, Train Accuracy: 0.7310, Val Loss: 1.2683, Val Accuracy: 0.6339 Epoch 4474/10000, Train Loss: 1.1883, Train Accuracy: 0.7366, Val Loss: 1.2682, Val Accuracy: 0.6339 Epoch 4475/10000, Train Loss: 1.1799, Train Accuracy: 0.7467, Val Loss: 1.2681, Val Accuracy: 0.6339 Epoch 4476/10000, Train Loss: 1.1989, Train Accuracy: 0.7121, Val Loss: 1.2680, Val Accuracy: 0.6339 Epoch 4477/10000, Train Loss: 1.1987, Train Accuracy: 0.7121, Val Loss: 1.2681, Val Accuracy: 0.6339 Epoch 4478/10000, Train Loss: 1.1935, Train Accuracy: 0.7221, Val Loss: 1.2679, Val Accuracy: 0.6339 Epoch 4479/10000, Train Loss: 1.1932, Train Accuracy: 0.7210, Val Loss: 1.2679, Val Accuracy: 0.6339 Epoch 4480/10000, Train Loss: 1.1969, Train Accuracy: 0.7243, Val Loss: 1.2677, Val Accuracy: 0.6339 Epoch 4481/10000, Train Loss: 1.1977, Train Accuracy: 0.7176, Val Loss: 1.2678, Val Accuracy: 0.6339 Epoch 4482/10000, Train Loss: 1.1832, Train Accuracy: 0.7411, Val Loss: 1.2679, Val Accuracy: 0.6339 Epoch 4483/10000, Train Loss: 1.1902, Train Accuracy: 0.7366, Val Loss: 1.2678, Val Accuracy: 0.6295 Epoch 4484/10000, Train Loss: 1.1846, Train Accuracy: 0.7333, Val Loss: 1.2678, Val Accuracy: 0.6295 Epoch 4485/10000, Train Loss: 1.1886, Train Accuracy: 0.7277, Val Loss: 1.2677, Val Accuracy: 0.6295 Epoch 4486/10000, Train Loss: 1.1909, Train Accuracy: 0.7277, Val Loss: 1.2678, Val Accuracy: 0.6295 Epoch 4487/10000, Train Loss: 1.1904, Train Accuracy: 0.7243, Val Loss: 1.2677, Val Accuracy: 0.6295 Epoch 4488/10000, Train Loss: 1.1778, Train Accuracy: 0.7489, Val Loss: 1.2677, Val Accuracy: 0.6339 Epoch 4489/10000, Train Loss: 1.1967, Train Accuracy: 0.7199, Val Loss: 1.2677, Val Accuracy: 0.6339 Epoch 4490/10000, Train Loss: 1.1865, Train Accuracy: 0.7310, Val Loss: 1.2676, Val Accuracy: 0.6384 Epoch 4491/10000, Train Loss: 1.1900, Train Accuracy: 0.7333, Val Loss: 1.2675, Val Accuracy: 0.6384 Epoch 4492/10000, Train Loss: 1.1939, Train Accuracy: 0.7333, Val Loss: 1.2676, Val Accuracy: 0.6384 Epoch 4493/10000, Train Loss: 1.1900, Train Accuracy: 0.7254, Val Loss: 1.2675, Val Accuracy: 0.6384 Epoch 4494/10000, Train Loss: 1.1992, Train Accuracy: 0.7154, Val Loss: 1.2674, Val Accuracy: 0.6384 Epoch 4495/10000, Train Loss: 1.2021, Train Accuracy: 0.7243, Val Loss: 1.2674, Val Accuracy: 0.6384 Epoch 4496/10000, Train Loss: 1.1870, Train Accuracy: 0.7310, Val Loss: 1.2674, Val Accuracy: 0.6384 Epoch 4497/10000, Train Loss: 1.2006, Train Accuracy: 0.7221, Val Loss: 1.2674, Val Accuracy: 0.6384 Epoch 4498/10000, Train Loss: 1.1907, Train Accuracy: 0.7299, Val Loss: 1.2673, Val Accuracy: 0.6384 Epoch 4499/10000, Train Loss: 1.1911, Train Accuracy: 0.7243, Val Loss: 1.2672, Val Accuracy: 0.6384 Epoch 4500/10000, Train Loss: 1.1900, Train Accuracy: 0.7199, Val Loss: 1.2673, Val Accuracy: 0.6429 Epoch 4501/10000, Train Loss: 1.1913, Train Accuracy: 0.7344, Val Loss: 1.2672, Val Accuracy: 0.6384 Epoch 4502/10000, Train Loss: 1.1942, Train Accuracy: 0.7199, Val Loss: 1.2672, Val Accuracy: 0.6339 Epoch 4503/10000, Train Loss: 1.1739, Train Accuracy: 0.7455, Val Loss: 1.2672, Val Accuracy: 0.6384 Epoch 4504/10000, Train Loss: 1.1951, Train Accuracy: 0.7199, Val Loss: 1.2670, Val Accuracy: 0.6339 Epoch 4505/10000, Train Loss: 1.2040, Train Accuracy: 0.7042, Val Loss: 1.2669, Val Accuracy: 0.6384 Epoch 4506/10000, Train Loss: 1.1845, Train Accuracy: 0.7411, Val Loss: 1.2668, Val Accuracy: 0.6384 Epoch 4507/10000, Train Loss: 1.1912, Train Accuracy: 0.7266, Val Loss: 1.2668, Val Accuracy: 0.6384 Epoch 4508/10000, Train Loss: 1.1833, Train Accuracy: 0.7400, Val Loss: 1.2668, Val Accuracy: 0.6384 Epoch 4509/10000, Train Loss: 1.1883, Train Accuracy: 0.7277, Val Loss: 1.2666, Val Accuracy: 0.6384 Epoch 4510/10000, Train Loss: 1.1916, Train Accuracy: 0.7321, Val Loss: 1.2666, Val Accuracy: 0.6384 Epoch 4511/10000, Train Loss: 1.1950, Train Accuracy: 0.7221, Val Loss: 1.2667, Val Accuracy: 0.6384 Epoch 4512/10000, Train Loss: 1.1995, Train Accuracy: 0.7221, Val Loss: 1.2666, Val Accuracy: 0.6339 Epoch 4513/10000, Train Loss: 1.1982, Train Accuracy: 0.7109, Val Loss: 1.2665, Val Accuracy: 0.6339 Epoch 4514/10000, Train Loss: 1.1865, Train Accuracy: 0.7344, Val Loss: 1.2664, Val Accuracy: 0.6295 Epoch 4515/10000, Train Loss: 1.1943, Train Accuracy: 0.7243, Val Loss: 1.2663, Val Accuracy: 0.6384 Epoch 4516/10000, Train Loss: 1.1976, Train Accuracy: 0.7109, Val Loss: 1.2663, Val Accuracy: 0.6384 Epoch 4517/10000, Train Loss: 1.1905, Train Accuracy: 0.7210, Val Loss: 1.2662, Val Accuracy: 0.6384 Epoch 4518/10000, Train Loss: 1.1862, Train Accuracy: 0.7355, Val Loss: 1.2662, Val Accuracy: 0.6384 Epoch 4519/10000, Train Loss: 1.1870, Train Accuracy: 0.7299, Val Loss: 1.2661, Val Accuracy: 0.6384 Epoch 4520/10000, Train Loss: 1.1938, Train Accuracy: 0.7243, Val Loss: 1.2660, Val Accuracy: 0.6384 Epoch 4521/10000, Train Loss: 1.1908, Train Accuracy: 0.7266, Val Loss: 1.2660, Val Accuracy: 0.6339 Epoch 4522/10000, Train Loss: 1.1885, Train Accuracy: 0.7299, Val Loss: 1.2659, Val Accuracy: 0.6384 Epoch 4523/10000, Train Loss: 1.1878, Train Accuracy: 0.7266, Val Loss: 1.2658, Val Accuracy: 0.6384 Epoch 4524/10000, Train Loss: 1.1833, Train Accuracy: 0.7400, Val Loss: 1.2658, Val Accuracy: 0.6339 Epoch 4525/10000, Train Loss: 1.1799, Train Accuracy: 0.7467, Val Loss: 1.2659, Val Accuracy: 0.6339 Epoch 4526/10000, Train Loss: 1.1976, Train Accuracy: 0.7199, Val Loss: 1.2657, Val Accuracy: 0.6384 Epoch 4527/10000, Train Loss: 1.1862, Train Accuracy: 0.7333, Val Loss: 1.2655, Val Accuracy: 0.6384 Epoch 4528/10000, Train Loss: 1.1835, Train Accuracy: 0.7355, Val Loss: 1.2655, Val Accuracy: 0.6384 Epoch 4529/10000, Train Loss: 1.1862, Train Accuracy: 0.7299, Val Loss: 1.2654, Val Accuracy: 0.6339 Epoch 4530/10000, Train Loss: 1.1935, Train Accuracy: 0.7266, Val Loss: 1.2654, Val Accuracy: 0.6339 Epoch 4531/10000, Train Loss: 1.1846, Train Accuracy: 0.7355, Val Loss: 1.2653, Val Accuracy: 0.6339 Epoch 4532/10000, Train Loss: 1.1842, Train Accuracy: 0.7411, Val Loss: 1.2652, Val Accuracy: 0.6339 Epoch 4533/10000, Train Loss: 1.1759, Train Accuracy: 0.7478, Val Loss: 1.2652, Val Accuracy: 0.6339 Epoch 4534/10000, Train Loss: 1.1775, Train Accuracy: 0.7411, Val Loss: 1.2651, Val Accuracy: 0.6384 Epoch 4535/10000, Train Loss: 1.1781, Train Accuracy: 0.7344, Val Loss: 1.2649, Val Accuracy: 0.6339 Epoch 4536/10000, Train Loss: 1.1838, Train Accuracy: 0.7321, Val Loss: 1.2648, Val Accuracy: 0.6384 Epoch 4537/10000, Train Loss: 1.1919, Train Accuracy: 0.7254, Val Loss: 1.2649, Val Accuracy: 0.6384 Epoch 4538/10000, Train Loss: 1.1980, Train Accuracy: 0.7243, Val Loss: 1.2648, Val Accuracy: 0.6384 Epoch 4539/10000, Train Loss: 1.1898, Train Accuracy: 0.7210, Val Loss: 1.2648, Val Accuracy: 0.6384 Epoch 4540/10000, Train Loss: 1.1910, Train Accuracy: 0.7333, Val Loss: 1.2648, Val Accuracy: 0.6429 Epoch 4541/10000, Train Loss: 1.1844, Train Accuracy: 0.7422, Val Loss: 1.2647, Val Accuracy: 0.6429 Epoch 4542/10000, Train Loss: 1.1890, Train Accuracy: 0.7321, Val Loss: 1.2648, Val Accuracy: 0.6429 Epoch 4543/10000, Train Loss: 1.1906, Train Accuracy: 0.7288, Val Loss: 1.2647, Val Accuracy: 0.6429 Epoch 4544/10000, Train Loss: 1.1868, Train Accuracy: 0.7388, Val Loss: 1.2647, Val Accuracy: 0.6429 Epoch 4545/10000, Train Loss: 1.1892, Train Accuracy: 0.7467, Val Loss: 1.2646, Val Accuracy: 0.6384 Epoch 4546/10000, Train Loss: 1.1783, Train Accuracy: 0.7533, Val Loss: 1.2645, Val Accuracy: 0.6384 Epoch 4547/10000, Train Loss: 1.1968, Train Accuracy: 0.7232, Val Loss: 1.2643, Val Accuracy: 0.6384 Epoch 4548/10000, Train Loss: 1.1871, Train Accuracy: 0.7277, Val Loss: 1.2645, Val Accuracy: 0.6384 Epoch 4549/10000, Train Loss: 1.1924, Train Accuracy: 0.7232, Val Loss: 1.2646, Val Accuracy: 0.6339 Epoch 4550/10000, Train Loss: 1.1858, Train Accuracy: 0.7199, Val Loss: 1.2646, Val Accuracy: 0.6384 Epoch 4551/10000, Train Loss: 1.1984, Train Accuracy: 0.7154, Val Loss: 1.2645, Val Accuracy: 0.6384 Epoch 4552/10000, Train Loss: 1.1839, Train Accuracy: 0.7355, Val Loss: 1.2644, Val Accuracy: 0.6384 Epoch 4553/10000, Train Loss: 1.1796, Train Accuracy: 0.7489, Val Loss: 1.2644, Val Accuracy: 0.6429 Epoch 4554/10000, Train Loss: 1.1896, Train Accuracy: 0.7299, Val Loss: 1.2643, Val Accuracy: 0.6384 Epoch 4555/10000, Train Loss: 1.1731, Train Accuracy: 0.7500, Val Loss: 1.2641, Val Accuracy: 0.6384 Epoch 4556/10000, Train Loss: 1.1778, Train Accuracy: 0.7500, Val Loss: 1.2640, Val Accuracy: 0.6429 Epoch 4557/10000, Train Loss: 1.1926, Train Accuracy: 0.7266, Val Loss: 1.2640, Val Accuracy: 0.6384 Epoch 4558/10000, Train Loss: 1.1989, Train Accuracy: 0.7199, Val Loss: 1.2640, Val Accuracy: 0.6339 Epoch 4559/10000, Train Loss: 1.1822, Train Accuracy: 0.7277, Val Loss: 1.2638, Val Accuracy: 0.6384 Epoch 4560/10000, Train Loss: 1.1871, Train Accuracy: 0.7388, Val Loss: 1.2639, Val Accuracy: 0.6384 Epoch 4561/10000, Train Loss: 1.1973, Train Accuracy: 0.7188, Val Loss: 1.2641, Val Accuracy: 0.6384 Epoch 4562/10000, Train Loss: 1.1839, Train Accuracy: 0.7388, Val Loss: 1.2639, Val Accuracy: 0.6384 Epoch 4563/10000, Train Loss: 1.1748, Train Accuracy: 0.7533, Val Loss: 1.2638, Val Accuracy: 0.6429 Epoch 4564/10000, Train Loss: 1.1910, Train Accuracy: 0.7266, Val Loss: 1.2638, Val Accuracy: 0.6429 Epoch 4565/10000, Train Loss: 1.1819, Train Accuracy: 0.7299, Val Loss: 1.2637, Val Accuracy: 0.6384 Epoch 4566/10000, Train Loss: 1.1841, Train Accuracy: 0.7355, Val Loss: 1.2635, Val Accuracy: 0.6384 Epoch 4567/10000, Train Loss: 1.1949, Train Accuracy: 0.7154, Val Loss: 1.2635, Val Accuracy: 0.6429 Epoch 4568/10000, Train Loss: 1.1851, Train Accuracy: 0.7243, Val Loss: 1.2634, Val Accuracy: 0.6429 Epoch 4569/10000, Train Loss: 1.1809, Train Accuracy: 0.7377, Val Loss: 1.2633, Val Accuracy: 0.6429 Epoch 4570/10000, Train Loss: 1.1803, Train Accuracy: 0.7344, Val Loss: 1.2633, Val Accuracy: 0.6429 Epoch 4571/10000, Train Loss: 1.1891, Train Accuracy: 0.7254, Val Loss: 1.2633, Val Accuracy: 0.6429 Epoch 4572/10000, Train Loss: 1.1813, Train Accuracy: 0.7310, Val Loss: 1.2633, Val Accuracy: 0.6429 Epoch 4573/10000, Train Loss: 1.1825, Train Accuracy: 0.7444, Val Loss: 1.2634, Val Accuracy: 0.6473 Epoch 4574/10000, Train Loss: 1.1865, Train Accuracy: 0.7254, Val Loss: 1.2633, Val Accuracy: 0.6429 Epoch 4575/10000, Train Loss: 1.1874, Train Accuracy: 0.7266, Val Loss: 1.2633, Val Accuracy: 0.6429 Epoch 4576/10000, Train Loss: 1.1904, Train Accuracy: 0.7355, Val Loss: 1.2631, Val Accuracy: 0.6429 Epoch 4577/10000, Train Loss: 1.1854, Train Accuracy: 0.7400, Val Loss: 1.2629, Val Accuracy: 0.6429 Epoch 4578/10000, Train Loss: 1.1841, Train Accuracy: 0.7388, Val Loss: 1.2629, Val Accuracy: 0.6429 Epoch 4579/10000, Train Loss: 1.1939, Train Accuracy: 0.7221, Val Loss: 1.2629, Val Accuracy: 0.6429 Epoch 4580/10000, Train Loss: 1.1901, Train Accuracy: 0.7344, Val Loss: 1.2628, Val Accuracy: 0.6429 Epoch 4581/10000, Train Loss: 1.1843, Train Accuracy: 0.7344, Val Loss: 1.2626, Val Accuracy: 0.6429 Epoch 4582/10000, Train Loss: 1.1895, Train Accuracy: 0.7266, Val Loss: 1.2627, Val Accuracy: 0.6429 Epoch 4583/10000, Train Loss: 1.1916, Train Accuracy: 0.7310, Val Loss: 1.2627, Val Accuracy: 0.6429 Epoch 4584/10000, Train Loss: 1.1919, Train Accuracy: 0.7176, Val Loss: 1.2628, Val Accuracy: 0.6429 Epoch 4585/10000, Train Loss: 1.1748, Train Accuracy: 0.7489, Val Loss: 1.2627, Val Accuracy: 0.6429 Epoch 4586/10000, Train Loss: 1.1960, Train Accuracy: 0.7254, Val Loss: 1.2626, Val Accuracy: 0.6429 Epoch 4587/10000, Train Loss: 1.1899, Train Accuracy: 0.7277, Val Loss: 1.2627, Val Accuracy: 0.6473 Epoch 4588/10000, Train Loss: 1.1867, Train Accuracy: 0.7321, Val Loss: 1.2627, Val Accuracy: 0.6473 Epoch 4589/10000, Train Loss: 1.1818, Train Accuracy: 0.7400, Val Loss: 1.2627, Val Accuracy: 0.6473 Epoch 4590/10000, Train Loss: 1.1782, Train Accuracy: 0.7388, Val Loss: 1.2627, Val Accuracy: 0.6429 Epoch 4591/10000, Train Loss: 1.1868, Train Accuracy: 0.7321, Val Loss: 1.2626, Val Accuracy: 0.6429 Epoch 4592/10000, Train Loss: 1.1806, Train Accuracy: 0.7377, Val Loss: 1.2626, Val Accuracy: 0.6429 Epoch 4593/10000, Train Loss: 1.1788, Train Accuracy: 0.7366, Val Loss: 1.2626, Val Accuracy: 0.6429 Epoch 4594/10000, Train Loss: 1.1862, Train Accuracy: 0.7433, Val Loss: 1.2625, Val Accuracy: 0.6473 Epoch 4595/10000, Train Loss: 1.1815, Train Accuracy: 0.7344, Val Loss: 1.2625, Val Accuracy: 0.6429 Epoch 4596/10000, Train Loss: 1.1831, Train Accuracy: 0.7377, Val Loss: 1.2625, Val Accuracy: 0.6429 Epoch 4597/10000, Train Loss: 1.1971, Train Accuracy: 0.7210, Val Loss: 1.2624, Val Accuracy: 0.6429 Epoch 4598/10000, Train Loss: 1.1814, Train Accuracy: 0.7288, Val Loss: 1.2622, Val Accuracy: 0.6429 Epoch 4599/10000, Train Loss: 1.1763, Train Accuracy: 0.7422, Val Loss: 1.2621, Val Accuracy: 0.6429 Epoch 4600/10000, Train Loss: 1.1860, Train Accuracy: 0.7299, Val Loss: 1.2623, Val Accuracy: 0.6473 Epoch 4601/10000, Train Loss: 1.1722, Train Accuracy: 0.7422, Val Loss: 1.2622, Val Accuracy: 0.6473 Epoch 4602/10000, Train Loss: 1.1883, Train Accuracy: 0.7266, Val Loss: 1.2620, Val Accuracy: 0.6473 Epoch 4603/10000, Train Loss: 1.1749, Train Accuracy: 0.7467, Val Loss: 1.2619, Val Accuracy: 0.6473 Epoch 4604/10000, Train Loss: 1.1881, Train Accuracy: 0.7321, Val Loss: 1.2618, Val Accuracy: 0.6429 Epoch 4605/10000, Train Loss: 1.1963, Train Accuracy: 0.7210, Val Loss: 1.2618, Val Accuracy: 0.6429 Epoch 4606/10000, Train Loss: 1.1766, Train Accuracy: 0.7388, Val Loss: 1.2618, Val Accuracy: 0.6429 Epoch 4607/10000, Train Loss: 1.1670, Train Accuracy: 0.7600, Val Loss: 1.2618, Val Accuracy: 0.6429 Epoch 4608/10000, Train Loss: 1.1900, Train Accuracy: 0.7288, Val Loss: 1.2617, Val Accuracy: 0.6384 Epoch 4609/10000, Train Loss: 1.1878, Train Accuracy: 0.7288, Val Loss: 1.2616, Val Accuracy: 0.6429 Epoch 4610/10000, Train Loss: 1.1812, Train Accuracy: 0.7299, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4611/10000, Train Loss: 1.1829, Train Accuracy: 0.7344, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4612/10000, Train Loss: 1.2007, Train Accuracy: 0.7065, Val Loss: 1.2615, Val Accuracy: 0.6429 Epoch 4613/10000, Train Loss: 1.1884, Train Accuracy: 0.7333, Val Loss: 1.2614, Val Accuracy: 0.6473 Epoch 4614/10000, Train Loss: 1.1947, Train Accuracy: 0.7266, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4615/10000, Train Loss: 1.1843, Train Accuracy: 0.7333, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4616/10000, Train Loss: 1.1852, Train Accuracy: 0.7344, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4617/10000, Train Loss: 1.1919, Train Accuracy: 0.7221, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4618/10000, Train Loss: 1.1998, Train Accuracy: 0.7176, Val Loss: 1.2614, Val Accuracy: 0.6429 Epoch 4619/10000, Train Loss: 1.1761, Train Accuracy: 0.7422, Val Loss: 1.2612, Val Accuracy: 0.6429 Epoch 4620/10000, Train Loss: 1.1658, Train Accuracy: 0.7489, Val Loss: 1.2612, Val Accuracy: 0.6429 Epoch 4621/10000, Train Loss: 1.1804, Train Accuracy: 0.7478, Val Loss: 1.2610, Val Accuracy: 0.6429 Epoch 4622/10000, Train Loss: 1.1799, Train Accuracy: 0.7344, Val Loss: 1.2610, Val Accuracy: 0.6429 Epoch 4623/10000, Train Loss: 1.1807, Train Accuracy: 0.7433, Val Loss: 1.2610, Val Accuracy: 0.6429 Epoch 4624/10000, Train Loss: 1.1837, Train Accuracy: 0.7277, Val Loss: 1.2610, Val Accuracy: 0.6429 Epoch 4625/10000, Train Loss: 1.1789, Train Accuracy: 0.7321, Val Loss: 1.2608, Val Accuracy: 0.6384 Epoch 4626/10000, Train Loss: 1.1720, Train Accuracy: 0.7433, Val Loss: 1.2607, Val Accuracy: 0.6429 Epoch 4627/10000, Train Loss: 1.1873, Train Accuracy: 0.7232, Val Loss: 1.2607, Val Accuracy: 0.6429 Epoch 4628/10000, Train Loss: 1.1811, Train Accuracy: 0.7333, Val Loss: 1.2607, Val Accuracy: 0.6473 Epoch 4629/10000, Train Loss: 1.1818, Train Accuracy: 0.7310, Val Loss: 1.2607, Val Accuracy: 0.6473 Epoch 4630/10000, Train Loss: 1.1882, Train Accuracy: 0.7254, Val Loss: 1.2606, Val Accuracy: 0.6429 Epoch 4631/10000, Train Loss: 1.1831, Train Accuracy: 0.7366, Val Loss: 1.2606, Val Accuracy: 0.6473 Epoch 4632/10000, Train Loss: 1.1847, Train Accuracy: 0.7333, Val Loss: 1.2605, Val Accuracy: 0.6473 Epoch 4633/10000, Train Loss: 1.1644, Train Accuracy: 0.7612, Val Loss: 1.2605, Val Accuracy: 0.6429 Epoch 4634/10000, Train Loss: 1.1967, Train Accuracy: 0.7254, Val Loss: 1.2605, Val Accuracy: 0.6473 Epoch 4635/10000, Train Loss: 1.1730, Train Accuracy: 0.7433, Val Loss: 1.2605, Val Accuracy: 0.6518 Epoch 4636/10000, Train Loss: 1.1790, Train Accuracy: 0.7355, Val Loss: 1.2605, Val Accuracy: 0.6518 Epoch 4637/10000, Train Loss: 1.1952, Train Accuracy: 0.7121, Val Loss: 1.2605, Val Accuracy: 0.6473 Epoch 4638/10000, Train Loss: 1.1787, Train Accuracy: 0.7377, Val Loss: 1.2605, Val Accuracy: 0.6518 Epoch 4639/10000, Train Loss: 1.1774, Train Accuracy: 0.7533, Val Loss: 1.2603, Val Accuracy: 0.6518 Epoch 4640/10000, Train Loss: 1.1821, Train Accuracy: 0.7355, Val Loss: 1.2603, Val Accuracy: 0.6518 Epoch 4641/10000, Train Loss: 1.1744, Train Accuracy: 0.7500, Val Loss: 1.2603, Val Accuracy: 0.6518 Epoch 4642/10000, Train Loss: 1.1785, Train Accuracy: 0.7444, Val Loss: 1.2602, Val Accuracy: 0.6473 Epoch 4643/10000, Train Loss: 1.1907, Train Accuracy: 0.7243, Val Loss: 1.2602, Val Accuracy: 0.6473 Epoch 4644/10000, Train Loss: 1.1906, Train Accuracy: 0.7377, Val Loss: 1.2604, Val Accuracy: 0.6473 Epoch 4645/10000, Train Loss: 1.1836, Train Accuracy: 0.7400, Val Loss: 1.2603, Val Accuracy: 0.6473 Epoch 4646/10000, Train Loss: 1.1629, Train Accuracy: 0.7533, Val Loss: 1.2602, Val Accuracy: 0.6473 Epoch 4647/10000, Train Loss: 1.1888, Train Accuracy: 0.7254, Val Loss: 1.2602, Val Accuracy: 0.6518 Epoch 4648/10000, Train Loss: 1.1809, Train Accuracy: 0.7266, Val Loss: 1.2601, Val Accuracy: 0.6518 Epoch 4649/10000, Train Loss: 1.1832, Train Accuracy: 0.7310, Val Loss: 1.2602, Val Accuracy: 0.6518 Epoch 4650/10000, Train Loss: 1.1908, Train Accuracy: 0.7277, Val Loss: 1.2604, Val Accuracy: 0.6429 Epoch 4651/10000, Train Loss: 1.1908, Train Accuracy: 0.7266, Val Loss: 1.2603, Val Accuracy: 0.6518 Epoch 4652/10000, Train Loss: 1.1930, Train Accuracy: 0.7221, Val Loss: 1.2603, Val Accuracy: 0.6518 Epoch 4653/10000, Train Loss: 1.1822, Train Accuracy: 0.7366, Val Loss: 1.2601, Val Accuracy: 0.6473 Epoch 4654/10000, Train Loss: 1.1823, Train Accuracy: 0.7433, Val Loss: 1.2601, Val Accuracy: 0.6473 Epoch 4655/10000, Train Loss: 1.1882, Train Accuracy: 0.7299, Val Loss: 1.2600, Val Accuracy: 0.6518 Epoch 4656/10000, Train Loss: 1.1794, Train Accuracy: 0.7400, Val Loss: 1.2600, Val Accuracy: 0.6429 Epoch 4657/10000, Train Loss: 1.1861, Train Accuracy: 0.7243, Val Loss: 1.2602, Val Accuracy: 0.6473 Epoch 4658/10000, Train Loss: 1.1811, Train Accuracy: 0.7310, Val Loss: 1.2601, Val Accuracy: 0.6473 Epoch 4659/10000, Train Loss: 1.1800, Train Accuracy: 0.7411, Val Loss: 1.2597, Val Accuracy: 0.6429 Epoch 4660/10000, Train Loss: 1.1828, Train Accuracy: 0.7344, Val Loss: 1.2598, Val Accuracy: 0.6429 Epoch 4661/10000, Train Loss: 1.1880, Train Accuracy: 0.7355, Val Loss: 1.2599, Val Accuracy: 0.6473 Epoch 4662/10000, Train Loss: 1.1886, Train Accuracy: 0.7277, Val Loss: 1.2599, Val Accuracy: 0.6473 Epoch 4663/10000, Train Loss: 1.1867, Train Accuracy: 0.7277, Val Loss: 1.2597, Val Accuracy: 0.6473 Epoch 4664/10000, Train Loss: 1.1733, Train Accuracy: 0.7444, Val Loss: 1.2597, Val Accuracy: 0.6473 Epoch 4665/10000, Train Loss: 1.1763, Train Accuracy: 0.7478, Val Loss: 1.2594, Val Accuracy: 0.6518 Epoch 4666/10000, Train Loss: 1.1947, Train Accuracy: 0.7232, Val Loss: 1.2595, Val Accuracy: 0.6473 Epoch 4667/10000, Train Loss: 1.1833, Train Accuracy: 0.7344, Val Loss: 1.2595, Val Accuracy: 0.6473 Epoch 4668/10000, Train Loss: 1.1893, Train Accuracy: 0.7310, Val Loss: 1.2593, Val Accuracy: 0.6518 Epoch 4669/10000, Train Loss: 1.1764, Train Accuracy: 0.7422, Val Loss: 1.2595, Val Accuracy: 0.6429 Epoch 4670/10000, Train Loss: 1.1727, Train Accuracy: 0.7489, Val Loss: 1.2595, Val Accuracy: 0.6429 Epoch 4671/10000, Train Loss: 1.1928, Train Accuracy: 0.7277, Val Loss: 1.2594, Val Accuracy: 0.6429 Epoch 4672/10000, Train Loss: 1.1889, Train Accuracy: 0.7333, Val Loss: 1.2591, Val Accuracy: 0.6473 Epoch 4673/10000, Train Loss: 1.1841, Train Accuracy: 0.7333, Val Loss: 1.2590, Val Accuracy: 0.6473 Epoch 4674/10000, Train Loss: 1.1782, Train Accuracy: 0.7422, Val Loss: 1.2590, Val Accuracy: 0.6429 Epoch 4675/10000, Train Loss: 1.1791, Train Accuracy: 0.7422, Val Loss: 1.2589, Val Accuracy: 0.6429 Epoch 4676/10000, Train Loss: 1.1858, Train Accuracy: 0.7310, Val Loss: 1.2588, Val Accuracy: 0.6429 Epoch 4677/10000, Train Loss: 1.1928, Train Accuracy: 0.7277, Val Loss: 1.2587, Val Accuracy: 0.6429 Epoch 4678/10000, Train Loss: 1.1835, Train Accuracy: 0.7333, Val Loss: 1.2586, Val Accuracy: 0.6429 Epoch 4679/10000, Train Loss: 1.1590, Train Accuracy: 0.7600, Val Loss: 1.2585, Val Accuracy: 0.6429 Epoch 4680/10000, Train Loss: 1.1913, Train Accuracy: 0.7221, Val Loss: 1.2585, Val Accuracy: 0.6429 Epoch 4681/10000, Train Loss: 1.1897, Train Accuracy: 0.7288, Val Loss: 1.2583, Val Accuracy: 0.6473 Epoch 4682/10000, Train Loss: 1.1911, Train Accuracy: 0.7188, Val Loss: 1.2582, Val Accuracy: 0.6473 Epoch 4683/10000, Train Loss: 1.1783, Train Accuracy: 0.7433, Val Loss: 1.2582, Val Accuracy: 0.6473 Epoch 4684/10000, Train Loss: 1.1761, Train Accuracy: 0.7411, Val Loss: 1.2585, Val Accuracy: 0.6473 Epoch 4685/10000, Train Loss: 1.1727, Train Accuracy: 0.7422, Val Loss: 1.2584, Val Accuracy: 0.6473 Epoch 4686/10000, Train Loss: 1.1765, Train Accuracy: 0.7444, Val Loss: 1.2585, Val Accuracy: 0.6473 Epoch 4687/10000, Train Loss: 1.1892, Train Accuracy: 0.7232, Val Loss: 1.2586, Val Accuracy: 0.6473 Epoch 4688/10000, Train Loss: 1.1792, Train Accuracy: 0.7388, Val Loss: 1.2587, Val Accuracy: 0.6429 Epoch 4689/10000, Train Loss: 1.1817, Train Accuracy: 0.7310, Val Loss: 1.2586, Val Accuracy: 0.6429 Epoch 4690/10000, Train Loss: 1.1848, Train Accuracy: 0.7299, Val Loss: 1.2586, Val Accuracy: 0.6429 Epoch 4691/10000, Train Loss: 1.1843, Train Accuracy: 0.7377, Val Loss: 1.2583, Val Accuracy: 0.6429 Epoch 4692/10000, Train Loss: 1.1713, Train Accuracy: 0.7533, Val Loss: 1.2582, Val Accuracy: 0.6429 Epoch 4693/10000, Train Loss: 1.1794, Train Accuracy: 0.7422, Val Loss: 1.2581, Val Accuracy: 0.6429 Epoch 4694/10000, Train Loss: 1.1753, Train Accuracy: 0.7422, Val Loss: 1.2582, Val Accuracy: 0.6429 Epoch 4695/10000, Train Loss: 1.1819, Train Accuracy: 0.7266, Val Loss: 1.2580, Val Accuracy: 0.6473 Epoch 4696/10000, Train Loss: 1.1710, Train Accuracy: 0.7444, Val Loss: 1.2579, Val Accuracy: 0.6473 Epoch 4697/10000, Train Loss: 1.1714, Train Accuracy: 0.7567, Val Loss: 1.2579, Val Accuracy: 0.6473 Epoch 4698/10000, Train Loss: 1.1666, Train Accuracy: 0.7567, Val Loss: 1.2578, Val Accuracy: 0.6473 Epoch 4699/10000, Train Loss: 1.1800, Train Accuracy: 0.7366, Val Loss: 1.2578, Val Accuracy: 0.6429 Epoch 4700/10000, Train Loss: 1.1809, Train Accuracy: 0.7321, Val Loss: 1.2578, Val Accuracy: 0.6429 Epoch 4701/10000, Train Loss: 1.1745, Train Accuracy: 0.7545, Val Loss: 1.2577, Val Accuracy: 0.6429 Epoch 4702/10000, Train Loss: 1.1726, Train Accuracy: 0.7444, Val Loss: 1.2577, Val Accuracy: 0.6384 Epoch 4703/10000, Train Loss: 1.1878, Train Accuracy: 0.7210, Val Loss: 1.2575, Val Accuracy: 0.6384 Epoch 4704/10000, Train Loss: 1.1899, Train Accuracy: 0.7266, Val Loss: 1.2576, Val Accuracy: 0.6384 Epoch 4705/10000, Train Loss: 1.1892, Train Accuracy: 0.7221, Val Loss: 1.2576, Val Accuracy: 0.6429 Epoch 4706/10000, Train Loss: 1.1885, Train Accuracy: 0.7366, Val Loss: 1.2575, Val Accuracy: 0.6473 Epoch 4707/10000, Train Loss: 1.1690, Train Accuracy: 0.7455, Val Loss: 1.2575, Val Accuracy: 0.6473 Epoch 4708/10000, Train Loss: 1.1785, Train Accuracy: 0.7388, Val Loss: 1.2576, Val Accuracy: 0.6473 Epoch 4709/10000, Train Loss: 1.1767, Train Accuracy: 0.7411, Val Loss: 1.2574, Val Accuracy: 0.6473 Epoch 4710/10000, Train Loss: 1.1854, Train Accuracy: 0.7333, Val Loss: 1.2575, Val Accuracy: 0.6473 Epoch 4711/10000, Train Loss: 1.1809, Train Accuracy: 0.7377, Val Loss: 1.2575, Val Accuracy: 0.6429 Epoch 4712/10000, Train Loss: 1.1741, Train Accuracy: 0.7422, Val Loss: 1.2574, Val Accuracy: 0.6384 Epoch 4713/10000, Train Loss: 1.1700, Train Accuracy: 0.7467, Val Loss: 1.2573, Val Accuracy: 0.6384 Epoch 4714/10000, Train Loss: 1.1868, Train Accuracy: 0.7266, Val Loss: 1.2573, Val Accuracy: 0.6384 Epoch 4715/10000, Train Loss: 1.1788, Train Accuracy: 0.7377, Val Loss: 1.2572, Val Accuracy: 0.6384 Epoch 4716/10000, Train Loss: 1.1799, Train Accuracy: 0.7366, Val Loss: 1.2572, Val Accuracy: 0.6384 Epoch 4717/10000, Train Loss: 1.1762, Train Accuracy: 0.7366, Val Loss: 1.2570, Val Accuracy: 0.6429 Epoch 4718/10000, Train Loss: 1.1659, Train Accuracy: 0.7556, Val Loss: 1.2569, Val Accuracy: 0.6429 Epoch 4719/10000, Train Loss: 1.1696, Train Accuracy: 0.7411, Val Loss: 1.2569, Val Accuracy: 0.6429 Epoch 4720/10000, Train Loss: 1.1851, Train Accuracy: 0.7277, Val Loss: 1.2566, Val Accuracy: 0.6429 Epoch 4721/10000, Train Loss: 1.1762, Train Accuracy: 0.7433, Val Loss: 1.2566, Val Accuracy: 0.6384 Epoch 4722/10000, Train Loss: 1.1631, Train Accuracy: 0.7556, Val Loss: 1.2566, Val Accuracy: 0.6384 Epoch 4723/10000, Train Loss: 1.1864, Train Accuracy: 0.7299, Val Loss: 1.2566, Val Accuracy: 0.6429 Epoch 4724/10000, Train Loss: 1.1819, Train Accuracy: 0.7333, Val Loss: 1.2568, Val Accuracy: 0.6384 Epoch 4725/10000, Train Loss: 1.1837, Train Accuracy: 0.7321, Val Loss: 1.2566, Val Accuracy: 0.6429 Epoch 4726/10000, Train Loss: 1.1691, Train Accuracy: 0.7556, Val Loss: 1.2567, Val Accuracy: 0.6429 Epoch 4727/10000, Train Loss: 1.1697, Train Accuracy: 0.7511, Val Loss: 1.2567, Val Accuracy: 0.6384 Epoch 4728/10000, Train Loss: 1.1806, Train Accuracy: 0.7266, Val Loss: 1.2566, Val Accuracy: 0.6429 Epoch 4729/10000, Train Loss: 1.1848, Train Accuracy: 0.7355, Val Loss: 1.2564, Val Accuracy: 0.6473 Epoch 4730/10000, Train Loss: 1.1773, Train Accuracy: 0.7467, Val Loss: 1.2564, Val Accuracy: 0.6473 Epoch 4731/10000, Train Loss: 1.1790, Train Accuracy: 0.7377, Val Loss: 1.2561, Val Accuracy: 0.6518 Epoch 4732/10000, Train Loss: 1.1883, Train Accuracy: 0.7299, Val Loss: 1.2561, Val Accuracy: 0.6473 Epoch 4733/10000, Train Loss: 1.1847, Train Accuracy: 0.7366, Val Loss: 1.2561, Val Accuracy: 0.6473 Epoch 4734/10000, Train Loss: 1.1773, Train Accuracy: 0.7500, Val Loss: 1.2561, Val Accuracy: 0.6429 Epoch 4735/10000, Train Loss: 1.1901, Train Accuracy: 0.7266, Val Loss: 1.2561, Val Accuracy: 0.6429 Epoch 4736/10000, Train Loss: 1.1726, Train Accuracy: 0.7444, Val Loss: 1.2560, Val Accuracy: 0.6429 Epoch 4737/10000, Train Loss: 1.1723, Train Accuracy: 0.7388, Val Loss: 1.2560, Val Accuracy: 0.6429 Epoch 4738/10000, Train Loss: 1.1804, Train Accuracy: 0.7321, Val Loss: 1.2561, Val Accuracy: 0.6473 Epoch 4739/10000, Train Loss: 1.1892, Train Accuracy: 0.7277, Val Loss: 1.2561, Val Accuracy: 0.6473 Epoch 4740/10000, Train Loss: 1.1733, Train Accuracy: 0.7444, Val Loss: 1.2559, Val Accuracy: 0.6518 Epoch 4741/10000, Train Loss: 1.1876, Train Accuracy: 0.7243, Val Loss: 1.2558, Val Accuracy: 0.6518 Epoch 4742/10000, Train Loss: 1.1775, Train Accuracy: 0.7422, Val Loss: 1.2558, Val Accuracy: 0.6473 Epoch 4743/10000, Train Loss: 1.1779, Train Accuracy: 0.7321, Val Loss: 1.2557, Val Accuracy: 0.6473 Epoch 4744/10000, Train Loss: 1.1748, Train Accuracy: 0.7433, Val Loss: 1.2557, Val Accuracy: 0.6473 Epoch 4745/10000, Train Loss: 1.1941, Train Accuracy: 0.7199, Val Loss: 1.2557, Val Accuracy: 0.6473 Epoch 4746/10000, Train Loss: 1.1758, Train Accuracy: 0.7366, Val Loss: 1.2554, Val Accuracy: 0.6518 Epoch 4747/10000, Train Loss: 1.1725, Train Accuracy: 0.7433, Val Loss: 1.2554, Val Accuracy: 0.6518 Epoch 4748/10000, Train Loss: 1.1815, Train Accuracy: 0.7344, Val Loss: 1.2553, Val Accuracy: 0.6473 Epoch 4749/10000, Train Loss: 1.1798, Train Accuracy: 0.7355, Val Loss: 1.2554, Val Accuracy: 0.6429 Epoch 4750/10000, Train Loss: 1.1811, Train Accuracy: 0.7444, Val Loss: 1.2556, Val Accuracy: 0.6429 Epoch 4751/10000, Train Loss: 1.1878, Train Accuracy: 0.7176, Val Loss: 1.2555, Val Accuracy: 0.6518 Epoch 4752/10000, Train Loss: 1.1869, Train Accuracy: 0.7333, Val Loss: 1.2554, Val Accuracy: 0.6518 Epoch 4753/10000, Train Loss: 1.1771, Train Accuracy: 0.7388, Val Loss: 1.2555, Val Accuracy: 0.6473 Epoch 4754/10000, Train Loss: 1.1846, Train Accuracy: 0.7243, Val Loss: 1.2552, Val Accuracy: 0.6473 Epoch 4755/10000, Train Loss: 1.1729, Train Accuracy: 0.7489, Val Loss: 1.2551, Val Accuracy: 0.6518 Epoch 4756/10000, Train Loss: 1.1769, Train Accuracy: 0.7310, Val Loss: 1.2550, Val Accuracy: 0.6518 Epoch 4757/10000, Train Loss: 1.1789, Train Accuracy: 0.7310, Val Loss: 1.2551, Val Accuracy: 0.6518 Epoch 4758/10000, Train Loss: 1.1770, Train Accuracy: 0.7388, Val Loss: 1.2549, Val Accuracy: 0.6562 Epoch 4759/10000, Train Loss: 1.1656, Train Accuracy: 0.7511, Val Loss: 1.2547, Val Accuracy: 0.6518 Epoch 4760/10000, Train Loss: 1.1745, Train Accuracy: 0.7455, Val Loss: 1.2547, Val Accuracy: 0.6518 Epoch 4761/10000, Train Loss: 1.1669, Train Accuracy: 0.7511, Val Loss: 1.2548, Val Accuracy: 0.6473 Epoch 4762/10000, Train Loss: 1.1619, Train Accuracy: 0.7511, Val Loss: 1.2549, Val Accuracy: 0.6473 Epoch 4763/10000, Train Loss: 1.1813, Train Accuracy: 0.7388, Val Loss: 1.2550, Val Accuracy: 0.6473 Epoch 4764/10000, Train Loss: 1.1757, Train Accuracy: 0.7433, Val Loss: 1.2549, Val Accuracy: 0.6473 Epoch 4765/10000, Train Loss: 1.1789, Train Accuracy: 0.7377, Val Loss: 1.2550, Val Accuracy: 0.6473 Epoch 4766/10000, Train Loss: 1.1764, Train Accuracy: 0.7377, Val Loss: 1.2550, Val Accuracy: 0.6473 Epoch 4767/10000, Train Loss: 1.1779, Train Accuracy: 0.7377, Val Loss: 1.2549, Val Accuracy: 0.6562 Epoch 4768/10000, Train Loss: 1.1676, Train Accuracy: 0.7511, Val Loss: 1.2550, Val Accuracy: 0.6562 Epoch 4769/10000, Train Loss: 1.1724, Train Accuracy: 0.7511, Val Loss: 1.2549, Val Accuracy: 0.6562 Epoch 4770/10000, Train Loss: 1.1890, Train Accuracy: 0.7221, Val Loss: 1.2547, Val Accuracy: 0.6607 Epoch 4771/10000, Train Loss: 1.1762, Train Accuracy: 0.7511, Val Loss: 1.2545, Val Accuracy: 0.6562 Epoch 4772/10000, Train Loss: 1.1693, Train Accuracy: 0.7522, Val Loss: 1.2545, Val Accuracy: 0.6518 Epoch 4773/10000, Train Loss: 1.1639, Train Accuracy: 0.7623, Val Loss: 1.2545, Val Accuracy: 0.6562 Epoch 4774/10000, Train Loss: 1.1679, Train Accuracy: 0.7478, Val Loss: 1.2546, Val Accuracy: 0.6518 Epoch 4775/10000, Train Loss: 1.1897, Train Accuracy: 0.7221, Val Loss: 1.2545, Val Accuracy: 0.6518 Epoch 4776/10000, Train Loss: 1.1660, Train Accuracy: 0.7589, Val Loss: 1.2546, Val Accuracy: 0.6562 Epoch 4777/10000, Train Loss: 1.1789, Train Accuracy: 0.7355, Val Loss: 1.2544, Val Accuracy: 0.6562 Epoch 4778/10000, Train Loss: 1.1785, Train Accuracy: 0.7344, Val Loss: 1.2543, Val Accuracy: 0.6562 Epoch 4779/10000, Train Loss: 1.1715, Train Accuracy: 0.7455, Val Loss: 1.2541, Val Accuracy: 0.6607 Epoch 4780/10000, Train Loss: 1.1713, Train Accuracy: 0.7444, Val Loss: 1.2542, Val Accuracy: 0.6518 Epoch 4781/10000, Train Loss: 1.1765, Train Accuracy: 0.7478, Val Loss: 1.2541, Val Accuracy: 0.6562 Epoch 4782/10000, Train Loss: 1.1640, Train Accuracy: 0.7567, Val Loss: 1.2540, Val Accuracy: 0.6562 Epoch 4783/10000, Train Loss: 1.1786, Train Accuracy: 0.7333, Val Loss: 1.2540, Val Accuracy: 0.6562 Epoch 4784/10000, Train Loss: 1.1700, Train Accuracy: 0.7511, Val Loss: 1.2539, Val Accuracy: 0.6518 Epoch 4785/10000, Train Loss: 1.1706, Train Accuracy: 0.7511, Val Loss: 1.2538, Val Accuracy: 0.6518 Epoch 4786/10000, Train Loss: 1.1680, Train Accuracy: 0.7489, Val Loss: 1.2537, Val Accuracy: 0.6473 Epoch 4787/10000, Train Loss: 1.1762, Train Accuracy: 0.7355, Val Loss: 1.2538, Val Accuracy: 0.6518 Epoch 4788/10000, Train Loss: 1.1700, Train Accuracy: 0.7467, Val Loss: 1.2538, Val Accuracy: 0.6518 Epoch 4789/10000, Train Loss: 1.1631, Train Accuracy: 0.7545, Val Loss: 1.2537, Val Accuracy: 0.6518 Epoch 4790/10000, Train Loss: 1.1765, Train Accuracy: 0.7478, Val Loss: 1.2535, Val Accuracy: 0.6473 Epoch 4791/10000, Train Loss: 1.1779, Train Accuracy: 0.7400, Val Loss: 1.2534, Val Accuracy: 0.6473 Epoch 4792/10000, Train Loss: 1.1722, Train Accuracy: 0.7411, Val Loss: 1.2535, Val Accuracy: 0.6518 Epoch 4793/10000, Train Loss: 1.1724, Train Accuracy: 0.7377, Val Loss: 1.2538, Val Accuracy: 0.6429 Epoch 4794/10000, Train Loss: 1.1741, Train Accuracy: 0.7400, Val Loss: 1.2537, Val Accuracy: 0.6429 Epoch 4795/10000, Train Loss: 1.1614, Train Accuracy: 0.7679, Val Loss: 1.2535, Val Accuracy: 0.6429 Epoch 4796/10000, Train Loss: 1.1699, Train Accuracy: 0.7467, Val Loss: 1.2536, Val Accuracy: 0.6429 Epoch 4797/10000, Train Loss: 1.1860, Train Accuracy: 0.7221, Val Loss: 1.2537, Val Accuracy: 0.6518 Epoch 4798/10000, Train Loss: 1.1663, Train Accuracy: 0.7444, Val Loss: 1.2536, Val Accuracy: 0.6518 Epoch 4799/10000, Train Loss: 1.1660, Train Accuracy: 0.7612, Val Loss: 1.2537, Val Accuracy: 0.6429 Epoch 4800/10000, Train Loss: 1.1726, Train Accuracy: 0.7411, Val Loss: 1.2537, Val Accuracy: 0.6473 Epoch 4801/10000, Train Loss: 1.1753, Train Accuracy: 0.7321, Val Loss: 1.2536, Val Accuracy: 0.6473 Epoch 4802/10000, Train Loss: 1.1659, Train Accuracy: 0.7511, Val Loss: 1.2536, Val Accuracy: 0.6473 Epoch 4803/10000, Train Loss: 1.1722, Train Accuracy: 0.7455, Val Loss: 1.2533, Val Accuracy: 0.6473 Epoch 4804/10000, Train Loss: 1.1769, Train Accuracy: 0.7400, Val Loss: 1.2531, Val Accuracy: 0.6473 Epoch 4805/10000, Train Loss: 1.1829, Train Accuracy: 0.7310, Val Loss: 1.2530, Val Accuracy: 0.6473 Epoch 4806/10000, Train Loss: 1.1804, Train Accuracy: 0.7288, Val Loss: 1.2529, Val Accuracy: 0.6473 Epoch 4807/10000, Train Loss: 1.1713, Train Accuracy: 0.7556, Val Loss: 1.2528, Val Accuracy: 0.6473 Epoch 4808/10000, Train Loss: 1.1862, Train Accuracy: 0.7210, Val Loss: 1.2527, Val Accuracy: 0.6518 Epoch 4809/10000, Train Loss: 1.1751, Train Accuracy: 0.7422, Val Loss: 1.2526, Val Accuracy: 0.6562 Epoch 4810/10000, Train Loss: 1.1769, Train Accuracy: 0.7467, Val Loss: 1.2527, Val Accuracy: 0.6518 Epoch 4811/10000, Train Loss: 1.1887, Train Accuracy: 0.7243, Val Loss: 1.2524, Val Accuracy: 0.6562 Epoch 4812/10000, Train Loss: 1.1845, Train Accuracy: 0.7344, Val Loss: 1.2523, Val Accuracy: 0.6518 Epoch 4813/10000, Train Loss: 1.1663, Train Accuracy: 0.7388, Val Loss: 1.2524, Val Accuracy: 0.6518 Epoch 4814/10000, Train Loss: 1.1786, Train Accuracy: 0.7321, Val Loss: 1.2524, Val Accuracy: 0.6518 Epoch 4815/10000, Train Loss: 1.1727, Train Accuracy: 0.7400, Val Loss: 1.2524, Val Accuracy: 0.6518 Epoch 4816/10000, Train Loss: 1.1729, Train Accuracy: 0.7455, Val Loss: 1.2523, Val Accuracy: 0.6562 Epoch 4817/10000, Train Loss: 1.1739, Train Accuracy: 0.7400, Val Loss: 1.2523, Val Accuracy: 0.6562 Epoch 4818/10000, Train Loss: 1.1735, Train Accuracy: 0.7455, Val Loss: 1.2522, Val Accuracy: 0.6562 Epoch 4819/10000, Train Loss: 1.1751, Train Accuracy: 0.7400, Val Loss: 1.2522, Val Accuracy: 0.6562 Epoch 4820/10000, Train Loss: 1.1698, Train Accuracy: 0.7500, Val Loss: 1.2520, Val Accuracy: 0.6607 Epoch 4821/10000, Train Loss: 1.1664, Train Accuracy: 0.7578, Val Loss: 1.2520, Val Accuracy: 0.6562 Epoch 4822/10000, Train Loss: 1.1751, Train Accuracy: 0.7433, Val Loss: 1.2521, Val Accuracy: 0.6518 Epoch 4823/10000, Train Loss: 1.1645, Train Accuracy: 0.7522, Val Loss: 1.2520, Val Accuracy: 0.6562 Epoch 4824/10000, Train Loss: 1.1726, Train Accuracy: 0.7422, Val Loss: 1.2521, Val Accuracy: 0.6562 Epoch 4825/10000, Train Loss: 1.1664, Train Accuracy: 0.7511, Val Loss: 1.2518, Val Accuracy: 0.6562 Epoch 4826/10000, Train Loss: 1.1661, Train Accuracy: 0.7455, Val Loss: 1.2517, Val Accuracy: 0.6562 Epoch 4827/10000, Train Loss: 1.1805, Train Accuracy: 0.7366, Val Loss: 1.2514, Val Accuracy: 0.6562 Epoch 4828/10000, Train Loss: 1.1642, Train Accuracy: 0.7578, Val Loss: 1.2513, Val Accuracy: 0.6562 Epoch 4829/10000, Train Loss: 1.1740, Train Accuracy: 0.7444, Val Loss: 1.2512, Val Accuracy: 0.6562 Epoch 4830/10000, Train Loss: 1.1598, Train Accuracy: 0.7612, Val Loss: 1.2511, Val Accuracy: 0.6607 Epoch 4831/10000, Train Loss: 1.1886, Train Accuracy: 0.7277, Val Loss: 1.2511, Val Accuracy: 0.6562 Epoch 4832/10000, Train Loss: 1.1700, Train Accuracy: 0.7511, Val Loss: 1.2510, Val Accuracy: 0.6562 Epoch 4833/10000, Train Loss: 1.1701, Train Accuracy: 0.7455, Val Loss: 1.2508, Val Accuracy: 0.6607 Epoch 4834/10000, Train Loss: 1.1759, Train Accuracy: 0.7455, Val Loss: 1.2509, Val Accuracy: 0.6607 Epoch 4835/10000, Train Loss: 1.1759, Train Accuracy: 0.7377, Val Loss: 1.2508, Val Accuracy: 0.6607 Epoch 4836/10000, Train Loss: 1.1709, Train Accuracy: 0.7478, Val Loss: 1.2507, Val Accuracy: 0.6607 Epoch 4837/10000, Train Loss: 1.1729, Train Accuracy: 0.7355, Val Loss: 1.2509, Val Accuracy: 0.6518 Epoch 4838/10000, Train Loss: 1.1768, Train Accuracy: 0.7411, Val Loss: 1.2508, Val Accuracy: 0.6562 Epoch 4839/10000, Train Loss: 1.1733, Train Accuracy: 0.7467, Val Loss: 1.2510, Val Accuracy: 0.6562 Epoch 4840/10000, Train Loss: 1.1696, Train Accuracy: 0.7411, Val Loss: 1.2510, Val Accuracy: 0.6562 Epoch 4841/10000, Train Loss: 1.1722, Train Accuracy: 0.7422, Val Loss: 1.2511, Val Accuracy: 0.6562 Epoch 4842/10000, Train Loss: 1.1725, Train Accuracy: 0.7455, Val Loss: 1.2508, Val Accuracy: 0.6562 Epoch 4843/10000, Train Loss: 1.1668, Train Accuracy: 0.7567, Val Loss: 1.2508, Val Accuracy: 0.6518 Epoch 4844/10000, Train Loss: 1.1668, Train Accuracy: 0.7533, Val Loss: 1.2506, Val Accuracy: 0.6518 Epoch 4845/10000, Train Loss: 1.1599, Train Accuracy: 0.7645, Val Loss: 1.2506, Val Accuracy: 0.6518 Epoch 4846/10000, Train Loss: 1.1715, Train Accuracy: 0.7411, Val Loss: 1.2507, Val Accuracy: 0.6562 Epoch 4847/10000, Train Loss: 1.1788, Train Accuracy: 0.7288, Val Loss: 1.2508, Val Accuracy: 0.6562 Epoch 4848/10000, Train Loss: 1.1755, Train Accuracy: 0.7411, Val Loss: 1.2508, Val Accuracy: 0.6562 Epoch 4849/10000, Train Loss: 1.1809, Train Accuracy: 0.7266, Val Loss: 1.2507, Val Accuracy: 0.6607 Epoch 4850/10000, Train Loss: 1.1684, Train Accuracy: 0.7444, Val Loss: 1.2504, Val Accuracy: 0.6607 Epoch 4851/10000, Train Loss: 1.1732, Train Accuracy: 0.7400, Val Loss: 1.2505, Val Accuracy: 0.6562 Epoch 4852/10000, Train Loss: 1.1640, Train Accuracy: 0.7556, Val Loss: 1.2504, Val Accuracy: 0.6562 Epoch 4853/10000, Train Loss: 1.1747, Train Accuracy: 0.7522, Val Loss: 1.2505, Val Accuracy: 0.6518 Epoch 4854/10000, Train Loss: 1.1749, Train Accuracy: 0.7433, Val Loss: 1.2502, Val Accuracy: 0.6562 Epoch 4855/10000, Train Loss: 1.1653, Train Accuracy: 0.7623, Val Loss: 1.2500, Val Accuracy: 0.6562 Epoch 4856/10000, Train Loss: 1.1731, Train Accuracy: 0.7444, Val Loss: 1.2500, Val Accuracy: 0.6518 Epoch 4857/10000, Train Loss: 1.1759, Train Accuracy: 0.7333, Val Loss: 1.2500, Val Accuracy: 0.6518 Epoch 4858/10000, Train Loss: 1.1715, Train Accuracy: 0.7433, Val Loss: 1.2501, Val Accuracy: 0.6562 Epoch 4859/10000, Train Loss: 1.1667, Train Accuracy: 0.7478, Val Loss: 1.2501, Val Accuracy: 0.6562 Epoch 4860/10000, Train Loss: 1.1679, Train Accuracy: 0.7467, Val Loss: 1.2500, Val Accuracy: 0.6562 Epoch 4861/10000, Train Loss: 1.1701, Train Accuracy: 0.7511, Val Loss: 1.2500, Val Accuracy: 0.6562 Epoch 4862/10000, Train Loss: 1.1629, Train Accuracy: 0.7522, Val Loss: 1.2499, Val Accuracy: 0.6562 Epoch 4863/10000, Train Loss: 1.1818, Train Accuracy: 0.7243, Val Loss: 1.2497, Val Accuracy: 0.6562 Epoch 4864/10000, Train Loss: 1.1540, Train Accuracy: 0.7656, Val Loss: 1.2495, Val Accuracy: 0.6518 Epoch 4865/10000, Train Loss: 1.1674, Train Accuracy: 0.7522, Val Loss: 1.2494, Val Accuracy: 0.6518 Epoch 4866/10000, Train Loss: 1.1808, Train Accuracy: 0.7344, Val Loss: 1.2494, Val Accuracy: 0.6518 Epoch 4867/10000, Train Loss: 1.1803, Train Accuracy: 0.7355, Val Loss: 1.2493, Val Accuracy: 0.6518 Epoch 4868/10000, Train Loss: 1.1726, Train Accuracy: 0.7411, Val Loss: 1.2493, Val Accuracy: 0.6562 Epoch 4869/10000, Train Loss: 1.1661, Train Accuracy: 0.7478, Val Loss: 1.2495, Val Accuracy: 0.6562 Epoch 4870/10000, Train Loss: 1.1740, Train Accuracy: 0.7500, Val Loss: 1.2494, Val Accuracy: 0.6562 Epoch 4871/10000, Train Loss: 1.1739, Train Accuracy: 0.7344, Val Loss: 1.2492, Val Accuracy: 0.6562 Epoch 4872/10000, Train Loss: 1.1727, Train Accuracy: 0.7467, Val Loss: 1.2493, Val Accuracy: 0.6562 Epoch 4873/10000, Train Loss: 1.1691, Train Accuracy: 0.7422, Val Loss: 1.2492, Val Accuracy: 0.6562 Epoch 4874/10000, Train Loss: 1.1671, Train Accuracy: 0.7455, Val Loss: 1.2490, Val Accuracy: 0.6607 Epoch 4875/10000, Train Loss: 1.1728, Train Accuracy: 0.7489, Val Loss: 1.2490, Val Accuracy: 0.6607 Epoch 4876/10000, Train Loss: 1.1637, Train Accuracy: 0.7522, Val Loss: 1.2489, Val Accuracy: 0.6607 Epoch 4877/10000, Train Loss: 1.1626, Train Accuracy: 0.7545, Val Loss: 1.2487, Val Accuracy: 0.6607 Epoch 4878/10000, Train Loss: 1.1631, Train Accuracy: 0.7612, Val Loss: 1.2485, Val Accuracy: 0.6562 Epoch 4879/10000, Train Loss: 1.1672, Train Accuracy: 0.7467, Val Loss: 1.2485, Val Accuracy: 0.6652 Epoch 4880/10000, Train Loss: 1.1661, Train Accuracy: 0.7489, Val Loss: 1.2484, Val Accuracy: 0.6652 Epoch 4881/10000, Train Loss: 1.1708, Train Accuracy: 0.7489, Val Loss: 1.2485, Val Accuracy: 0.6607 Epoch 4882/10000, Train Loss: 1.1696, Train Accuracy: 0.7455, Val Loss: 1.2485, Val Accuracy: 0.6562 Epoch 4883/10000, Train Loss: 1.1599, Train Accuracy: 0.7589, Val Loss: 1.2485, Val Accuracy: 0.6562 Epoch 4884/10000, Train Loss: 1.1641, Train Accuracy: 0.7478, Val Loss: 1.2485, Val Accuracy: 0.6562 Epoch 4885/10000, Train Loss: 1.1769, Train Accuracy: 0.7266, Val Loss: 1.2485, Val Accuracy: 0.6562 Epoch 4886/10000, Train Loss: 1.1716, Train Accuracy: 0.7500, Val Loss: 1.2484, Val Accuracy: 0.6562 Epoch 4887/10000, Train Loss: 1.1750, Train Accuracy: 0.7511, Val Loss: 1.2482, Val Accuracy: 0.6562 Epoch 4888/10000, Train Loss: 1.1733, Train Accuracy: 0.7455, Val Loss: 1.2482, Val Accuracy: 0.6562 Epoch 4889/10000, Train Loss: 1.1606, Train Accuracy: 0.7600, Val Loss: 1.2479, Val Accuracy: 0.6607 Epoch 4890/10000, Train Loss: 1.1659, Train Accuracy: 0.7522, Val Loss: 1.2478, Val Accuracy: 0.6607 Epoch 4891/10000, Train Loss: 1.1742, Train Accuracy: 0.7411, Val Loss: 1.2479, Val Accuracy: 0.6652 Epoch 4892/10000, Train Loss: 1.1594, Train Accuracy: 0.7634, Val Loss: 1.2478, Val Accuracy: 0.6562 Epoch 4893/10000, Train Loss: 1.1613, Train Accuracy: 0.7511, Val Loss: 1.2478, Val Accuracy: 0.6607 Epoch 4894/10000, Train Loss: 1.1672, Train Accuracy: 0.7567, Val Loss: 1.2478, Val Accuracy: 0.6652 Epoch 4895/10000, Train Loss: 1.1739, Train Accuracy: 0.7400, Val Loss: 1.2477, Val Accuracy: 0.6652 Epoch 4896/10000, Train Loss: 1.1602, Train Accuracy: 0.7634, Val Loss: 1.2476, Val Accuracy: 0.6652 Epoch 4897/10000, Train Loss: 1.1634, Train Accuracy: 0.7511, Val Loss: 1.2475, Val Accuracy: 0.6652 Epoch 4898/10000, Train Loss: 1.1664, Train Accuracy: 0.7511, Val Loss: 1.2475, Val Accuracy: 0.6652 Epoch 4899/10000, Train Loss: 1.1607, Train Accuracy: 0.7589, Val Loss: 1.2476, Val Accuracy: 0.6652 Epoch 4900/10000, Train Loss: 1.1718, Train Accuracy: 0.7556, Val Loss: 1.2476, Val Accuracy: 0.6652 Epoch 4901/10000, Train Loss: 1.1693, Train Accuracy: 0.7489, Val Loss: 1.2476, Val Accuracy: 0.6652 Epoch 4902/10000, Train Loss: 1.1629, Train Accuracy: 0.7489, Val Loss: 1.2475, Val Accuracy: 0.6652 Epoch 4903/10000, Train Loss: 1.1734, Train Accuracy: 0.7377, Val Loss: 1.2475, Val Accuracy: 0.6652 Epoch 4904/10000, Train Loss: 1.1760, Train Accuracy: 0.7400, Val Loss: 1.2475, Val Accuracy: 0.6652 Epoch 4905/10000, Train Loss: 1.1714, Train Accuracy: 0.7400, Val Loss: 1.2475, Val Accuracy: 0.6652 Epoch 4906/10000, Train Loss: 1.1743, Train Accuracy: 0.7467, Val Loss: 1.2477, Val Accuracy: 0.6652 Epoch 4907/10000, Train Loss: 1.1669, Train Accuracy: 0.7467, Val Loss: 1.2477, Val Accuracy: 0.6652 Epoch 4908/10000, Train Loss: 1.1670, Train Accuracy: 0.7589, Val Loss: 1.2478, Val Accuracy: 0.6652 Epoch 4909/10000, Train Loss: 1.1779, Train Accuracy: 0.7366, Val Loss: 1.2478, Val Accuracy: 0.6607 Epoch 4910/10000, Train Loss: 1.1692, Train Accuracy: 0.7511, Val Loss: 1.2478, Val Accuracy: 0.6607 Epoch 4911/10000, Train Loss: 1.1755, Train Accuracy: 0.7344, Val Loss: 1.2478, Val Accuracy: 0.6652 Epoch 4912/10000, Train Loss: 1.1631, Train Accuracy: 0.7545, Val Loss: 1.2479, Val Accuracy: 0.6607 Epoch 4913/10000, Train Loss: 1.1698, Train Accuracy: 0.7411, Val Loss: 1.2478, Val Accuracy: 0.6562 Epoch 4914/10000, Train Loss: 1.1745, Train Accuracy: 0.7310, Val Loss: 1.2477, Val Accuracy: 0.6607 Epoch 4915/10000, Train Loss: 1.1657, Train Accuracy: 0.7500, Val Loss: 1.2477, Val Accuracy: 0.6562 Epoch 4916/10000, Train Loss: 1.1669, Train Accuracy: 0.7567, Val Loss: 1.2477, Val Accuracy: 0.6562 Epoch 4917/10000, Train Loss: 1.1747, Train Accuracy: 0.7366, Val Loss: 1.2477, Val Accuracy: 0.6562 Epoch 4918/10000, Train Loss: 1.1600, Train Accuracy: 0.7589, Val Loss: 1.2475, Val Accuracy: 0.6607 Epoch 4919/10000, Train Loss: 1.1789, Train Accuracy: 0.7333, Val Loss: 1.2474, Val Accuracy: 0.6607 Epoch 4920/10000, Train Loss: 1.1645, Train Accuracy: 0.7522, Val Loss: 1.2473, Val Accuracy: 0.6652 Epoch 4921/10000, Train Loss: 1.1669, Train Accuracy: 0.7467, Val Loss: 1.2476, Val Accuracy: 0.6562 Epoch 4922/10000, Train Loss: 1.1690, Train Accuracy: 0.7489, Val Loss: 1.2474, Val Accuracy: 0.6607 Epoch 4923/10000, Train Loss: 1.1733, Train Accuracy: 0.7411, Val Loss: 1.2474, Val Accuracy: 0.6607 Epoch 4924/10000, Train Loss: 1.1540, Train Accuracy: 0.7522, Val Loss: 1.2474, Val Accuracy: 0.6607 Epoch 4925/10000, Train Loss: 1.1686, Train Accuracy: 0.7533, Val Loss: 1.2472, Val Accuracy: 0.6607 Epoch 4926/10000, Train Loss: 1.1584, Train Accuracy: 0.7612, Val Loss: 1.2471, Val Accuracy: 0.6652 Epoch 4927/10000, Train Loss: 1.1744, Train Accuracy: 0.7422, Val Loss: 1.2468, Val Accuracy: 0.6652 Epoch 4928/10000, Train Loss: 1.1771, Train Accuracy: 0.7299, Val Loss: 1.2468, Val Accuracy: 0.6652 Epoch 4929/10000, Train Loss: 1.1551, Train Accuracy: 0.7634, Val Loss: 1.2468, Val Accuracy: 0.6652 Epoch 4930/10000, Train Loss: 1.1748, Train Accuracy: 0.7400, Val Loss: 1.2468, Val Accuracy: 0.6652 Epoch 4931/10000, Train Loss: 1.1668, Train Accuracy: 0.7422, Val Loss: 1.2465, Val Accuracy: 0.6652 Epoch 4932/10000, Train Loss: 1.1644, Train Accuracy: 0.7511, Val Loss: 1.2465, Val Accuracy: 0.6652 Epoch 4933/10000, Train Loss: 1.1693, Train Accuracy: 0.7522, Val Loss: 1.2465, Val Accuracy: 0.6607 Epoch 4934/10000, Train Loss: 1.1661, Train Accuracy: 0.7489, Val Loss: 1.2467, Val Accuracy: 0.6607 Epoch 4935/10000, Train Loss: 1.1617, Train Accuracy: 0.7634, Val Loss: 1.2466, Val Accuracy: 0.6652 Epoch 4936/10000, Train Loss: 1.1672, Train Accuracy: 0.7511, Val Loss: 1.2465, Val Accuracy: 0.6652 Epoch 4937/10000, Train Loss: 1.1764, Train Accuracy: 0.7400, Val Loss: 1.2463, Val Accuracy: 0.6652 Epoch 4938/10000, Train Loss: 1.1585, Train Accuracy: 0.7567, Val Loss: 1.2464, Val Accuracy: 0.6652 Epoch 4939/10000, Train Loss: 1.1778, Train Accuracy: 0.7344, Val Loss: 1.2463, Val Accuracy: 0.6652 Epoch 4940/10000, Train Loss: 1.1744, Train Accuracy: 0.7444, Val Loss: 1.2463, Val Accuracy: 0.6607 Epoch 4941/10000, Train Loss: 1.1697, Train Accuracy: 0.7455, Val Loss: 1.2464, Val Accuracy: 0.6652 Epoch 4942/10000, Train Loss: 1.1618, Train Accuracy: 0.7556, Val Loss: 1.2462, Val Accuracy: 0.6696 Epoch 4943/10000, Train Loss: 1.1589, Train Accuracy: 0.7567, Val Loss: 1.2461, Val Accuracy: 0.6652 Epoch 4944/10000, Train Loss: 1.1506, Train Accuracy: 0.7634, Val Loss: 1.2460, Val Accuracy: 0.6652 Epoch 4945/10000, Train Loss: 1.1505, Train Accuracy: 0.7712, Val Loss: 1.2461, Val Accuracy: 0.6696 Epoch 4946/10000, Train Loss: 1.1665, Train Accuracy: 0.7589, Val Loss: 1.2461, Val Accuracy: 0.6652 Epoch 4947/10000, Train Loss: 1.1681, Train Accuracy: 0.7545, Val Loss: 1.2461, Val Accuracy: 0.6652 Epoch 4948/10000, Train Loss: 1.1748, Train Accuracy: 0.7377, Val Loss: 1.2461, Val Accuracy: 0.6652 Epoch 4949/10000, Train Loss: 1.1600, Train Accuracy: 0.7612, Val Loss: 1.2461, Val Accuracy: 0.6696 Epoch 4950/10000, Train Loss: 1.1688, Train Accuracy: 0.7489, Val Loss: 1.2458, Val Accuracy: 0.6696 Epoch 4951/10000, Train Loss: 1.1703, Train Accuracy: 0.7467, Val Loss: 1.2457, Val Accuracy: 0.6696 Epoch 4952/10000, Train Loss: 1.1628, Train Accuracy: 0.7656, Val Loss: 1.2455, Val Accuracy: 0.6696 Epoch 4953/10000, Train Loss: 1.1587, Train Accuracy: 0.7634, Val Loss: 1.2455, Val Accuracy: 0.6696 Epoch 4954/10000, Train Loss: 1.1577, Train Accuracy: 0.7589, Val Loss: 1.2453, Val Accuracy: 0.6696 Epoch 4955/10000, Train Loss: 1.1556, Train Accuracy: 0.7623, Val Loss: 1.2452, Val Accuracy: 0.6696 Epoch 4956/10000, Train Loss: 1.1643, Train Accuracy: 0.7556, Val Loss: 1.2453, Val Accuracy: 0.6696 Epoch 4957/10000, Train Loss: 1.1739, Train Accuracy: 0.7433, Val Loss: 1.2453, Val Accuracy: 0.6696 Epoch 4958/10000, Train Loss: 1.1674, Train Accuracy: 0.7478, Val Loss: 1.2453, Val Accuracy: 0.6696 Epoch 4959/10000, Train Loss: 1.1650, Train Accuracy: 0.7589, Val Loss: 1.2452, Val Accuracy: 0.6696 Epoch 4960/10000, Train Loss: 1.1726, Train Accuracy: 0.7511, Val Loss: 1.2452, Val Accuracy: 0.6696 Epoch 4961/10000, Train Loss: 1.1717, Train Accuracy: 0.7377, Val Loss: 1.2454, Val Accuracy: 0.6696 Epoch 4962/10000, Train Loss: 1.1818, Train Accuracy: 0.7344, Val Loss: 1.2452, Val Accuracy: 0.6696 Epoch 4963/10000, Train Loss: 1.1713, Train Accuracy: 0.7511, Val Loss: 1.2452, Val Accuracy: 0.6652 Epoch 4964/10000, Train Loss: 1.1600, Train Accuracy: 0.7612, Val Loss: 1.2452, Val Accuracy: 0.6652 Epoch 4965/10000, Train Loss: 1.1767, Train Accuracy: 0.7422, Val Loss: 1.2452, Val Accuracy: 0.6696 Epoch 4966/10000, Train Loss: 1.1675, Train Accuracy: 0.7422, Val Loss: 1.2451, Val Accuracy: 0.6696 Epoch 4967/10000, Train Loss: 1.1565, Train Accuracy: 0.7545, Val Loss: 1.2451, Val Accuracy: 0.6696 Epoch 4968/10000, Train Loss: 1.1638, Train Accuracy: 0.7500, Val Loss: 1.2449, Val Accuracy: 0.6696 Epoch 4969/10000, Train Loss: 1.1547, Train Accuracy: 0.7623, Val Loss: 1.2450, Val Accuracy: 0.6696 Epoch 4970/10000, Train Loss: 1.1734, Train Accuracy: 0.7355, Val Loss: 1.2450, Val Accuracy: 0.6696 Epoch 4971/10000, Train Loss: 1.1712, Train Accuracy: 0.7467, Val Loss: 1.2449, Val Accuracy: 0.6696 Epoch 4972/10000, Train Loss: 1.1793, Train Accuracy: 0.7344, Val Loss: 1.2448, Val Accuracy: 0.6696 Epoch 4973/10000, Train Loss: 1.1690, Train Accuracy: 0.7522, Val Loss: 1.2449, Val Accuracy: 0.6696 Epoch 4974/10000, Train Loss: 1.1657, Train Accuracy: 0.7444, Val Loss: 1.2448, Val Accuracy: 0.6696 Epoch 4975/10000, Train Loss: 1.1616, Train Accuracy: 0.7567, Val Loss: 1.2447, Val Accuracy: 0.6696 Epoch 4976/10000, Train Loss: 1.1630, Train Accuracy: 0.7478, Val Loss: 1.2446, Val Accuracy: 0.6696 Epoch 4977/10000, Train Loss: 1.1691, Train Accuracy: 0.7478, Val Loss: 1.2446, Val Accuracy: 0.6652 Epoch 4978/10000, Train Loss: 1.1732, Train Accuracy: 0.7489, Val Loss: 1.2448, Val Accuracy: 0.6652 Epoch 4979/10000, Train Loss: 1.1595, Train Accuracy: 0.7623, Val Loss: 1.2446, Val Accuracy: 0.6652 Epoch 4980/10000, Train Loss: 1.1672, Train Accuracy: 0.7455, Val Loss: 1.2442, Val Accuracy: 0.6696 Epoch 4981/10000, Train Loss: 1.1647, Train Accuracy: 0.7623, Val Loss: 1.2441, Val Accuracy: 0.6741 Epoch 4982/10000, Train Loss: 1.1639, Train Accuracy: 0.7444, Val Loss: 1.2442, Val Accuracy: 0.6741 Epoch 4983/10000, Train Loss: 1.1680, Train Accuracy: 0.7444, Val Loss: 1.2441, Val Accuracy: 0.6741 Epoch 4984/10000, Train Loss: 1.1432, Train Accuracy: 0.7846, Val Loss: 1.2441, Val Accuracy: 0.6741 Epoch 4985/10000, Train Loss: 1.1674, Train Accuracy: 0.7478, Val Loss: 1.2441, Val Accuracy: 0.6741 Epoch 4986/10000, Train Loss: 1.1516, Train Accuracy: 0.7712, Val Loss: 1.2440, Val Accuracy: 0.6741 Epoch 4987/10000, Train Loss: 1.1805, Train Accuracy: 0.7254, Val Loss: 1.2439, Val Accuracy: 0.6741 Epoch 4988/10000, Train Loss: 1.1521, Train Accuracy: 0.7667, Val Loss: 1.2438, Val Accuracy: 0.6741 Epoch 4989/10000, Train Loss: 1.1681, Train Accuracy: 0.7478, Val Loss: 1.2438, Val Accuracy: 0.6741 Epoch 4990/10000, Train Loss: 1.1592, Train Accuracy: 0.7656, Val Loss: 1.2436, Val Accuracy: 0.6741 Epoch 4991/10000, Train Loss: 1.1748, Train Accuracy: 0.7489, Val Loss: 1.2434, Val Accuracy: 0.6741 Epoch 4992/10000, Train Loss: 1.1701, Train Accuracy: 0.7455, Val Loss: 1.2434, Val Accuracy: 0.6741 Epoch 4993/10000, Train Loss: 1.1775, Train Accuracy: 0.7511, Val Loss: 1.2433, Val Accuracy: 0.6741 Epoch 4994/10000, Train Loss: 1.1597, Train Accuracy: 0.7656, Val Loss: 1.2433, Val Accuracy: 0.6741 Epoch 4995/10000, Train Loss: 1.1592, Train Accuracy: 0.7612, Val Loss: 1.2432, Val Accuracy: 0.6741 Epoch 4996/10000, Train Loss: 1.1763, Train Accuracy: 0.7344, Val Loss: 1.2432, Val Accuracy: 0.6741 Epoch 4997/10000, Train Loss: 1.1617, Train Accuracy: 0.7600, Val Loss: 1.2431, Val Accuracy: 0.6741 Epoch 4998/10000, Train Loss: 1.1615, Train Accuracy: 0.7600, Val Loss: 1.2431, Val Accuracy: 0.6741 Epoch 4999/10000, Train Loss: 1.1623, Train Accuracy: 0.7556, Val Loss: 1.2431, Val Accuracy: 0.6741 Epoch 5000/10000, Train Loss: 1.1632, Train Accuracy: 0.7567, Val Loss: 1.2430, Val Accuracy: 0.6741 Epoch 5001/10000, Train Loss: 1.1579, Train Accuracy: 0.7623, Val Loss: 1.2429, Val Accuracy: 0.6741 Epoch 5002/10000, Train Loss: 1.1563, Train Accuracy: 0.7623, Val Loss: 1.2429, Val Accuracy: 0.6741 Epoch 5003/10000, Train Loss: 1.1518, Train Accuracy: 0.7746, Val Loss: 1.2428, Val Accuracy: 0.6741 Epoch 5004/10000, Train Loss: 1.1664, Train Accuracy: 0.7467, Val Loss: 1.2427, Val Accuracy: 0.6741 Epoch 5005/10000, Train Loss: 1.1655, Train Accuracy: 0.7511, Val Loss: 1.2427, Val Accuracy: 0.6741 Epoch 5006/10000, Train Loss: 1.1700, Train Accuracy: 0.7411, Val Loss: 1.2427, Val Accuracy: 0.6741 Epoch 5007/10000, Train Loss: 1.1716, Train Accuracy: 0.7433, Val Loss: 1.2428, Val Accuracy: 0.6741 Epoch 5008/10000, Train Loss: 1.1688, Train Accuracy: 0.7478, Val Loss: 1.2427, Val Accuracy: 0.6741 Epoch 5009/10000, Train Loss: 1.1606, Train Accuracy: 0.7511, Val Loss: 1.2427, Val Accuracy: 0.6741 Epoch 5010/10000, Train Loss: 1.1655, Train Accuracy: 0.7511, Val Loss: 1.2425, Val Accuracy: 0.6741 Epoch 5011/10000, Train Loss: 1.1675, Train Accuracy: 0.7455, Val Loss: 1.2424, Val Accuracy: 0.6741 Epoch 5012/10000, Train Loss: 1.1528, Train Accuracy: 0.7623, Val Loss: 1.2423, Val Accuracy: 0.6741 Epoch 5013/10000, Train Loss: 1.1657, Train Accuracy: 0.7500, Val Loss: 1.2425, Val Accuracy: 0.6741 Epoch 5014/10000, Train Loss: 1.1610, Train Accuracy: 0.7545, Val Loss: 1.2424, Val Accuracy: 0.6741 Epoch 5015/10000, Train Loss: 1.1491, Train Accuracy: 0.7734, Val Loss: 1.2422, Val Accuracy: 0.6741 Epoch 5016/10000, Train Loss: 1.1747, Train Accuracy: 0.7455, Val Loss: 1.2422, Val Accuracy: 0.6741 Epoch 5017/10000, Train Loss: 1.1699, Train Accuracy: 0.7467, Val Loss: 1.2421, Val Accuracy: 0.6741 Epoch 5018/10000, Train Loss: 1.1638, Train Accuracy: 0.7500, Val Loss: 1.2420, Val Accuracy: 0.6741 Epoch 5019/10000, Train Loss: 1.1598, Train Accuracy: 0.7589, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5020/10000, Train Loss: 1.1607, Train Accuracy: 0.7612, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5021/10000, Train Loss: 1.1559, Train Accuracy: 0.7634, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5022/10000, Train Loss: 1.1793, Train Accuracy: 0.7321, Val Loss: 1.2415, Val Accuracy: 0.6741 Epoch 5023/10000, Train Loss: 1.1745, Train Accuracy: 0.7388, Val Loss: 1.2415, Val Accuracy: 0.6741 Epoch 5024/10000, Train Loss: 1.1662, Train Accuracy: 0.7567, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5025/10000, Train Loss: 1.1635, Train Accuracy: 0.7612, Val Loss: 1.2414, Val Accuracy: 0.6741 Epoch 5026/10000, Train Loss: 1.1666, Train Accuracy: 0.7433, Val Loss: 1.2417, Val Accuracy: 0.6741 Epoch 5027/10000, Train Loss: 1.1568, Train Accuracy: 0.7679, Val Loss: 1.2417, Val Accuracy: 0.6741 Epoch 5028/10000, Train Loss: 1.1474, Train Accuracy: 0.7712, Val Loss: 1.2418, Val Accuracy: 0.6741 Epoch 5029/10000, Train Loss: 1.1577, Train Accuracy: 0.7589, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5030/10000, Train Loss: 1.1615, Train Accuracy: 0.7612, Val Loss: 1.2418, Val Accuracy: 0.6741 Epoch 5031/10000, Train Loss: 1.1538, Train Accuracy: 0.7734, Val Loss: 1.2418, Val Accuracy: 0.6696 Epoch 5032/10000, Train Loss: 1.1603, Train Accuracy: 0.7556, Val Loss: 1.2419, Val Accuracy: 0.6696 Epoch 5033/10000, Train Loss: 1.1719, Train Accuracy: 0.7467, Val Loss: 1.2417, Val Accuracy: 0.6696 Epoch 5034/10000, Train Loss: 1.1634, Train Accuracy: 0.7455, Val Loss: 1.2417, Val Accuracy: 0.6696 Epoch 5035/10000, Train Loss: 1.1532, Train Accuracy: 0.7623, Val Loss: 1.2418, Val Accuracy: 0.6696 Epoch 5036/10000, Train Loss: 1.1668, Train Accuracy: 0.7511, Val Loss: 1.2419, Val Accuracy: 0.6741 Epoch 5037/10000, Train Loss: 1.1702, Train Accuracy: 0.7455, Val Loss: 1.2419, Val Accuracy: 0.6741 Epoch 5038/10000, Train Loss: 1.1667, Train Accuracy: 0.7511, Val Loss: 1.2419, Val Accuracy: 0.6741 Epoch 5039/10000, Train Loss: 1.1694, Train Accuracy: 0.7388, Val Loss: 1.2416, Val Accuracy: 0.6786 Epoch 5040/10000, Train Loss: 1.1839, Train Accuracy: 0.7266, Val Loss: 1.2413, Val Accuracy: 0.6741 Epoch 5041/10000, Train Loss: 1.1601, Train Accuracy: 0.7511, Val Loss: 1.2415, Val Accuracy: 0.6741 Epoch 5042/10000, Train Loss: 1.1618, Train Accuracy: 0.7444, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5043/10000, Train Loss: 1.1597, Train Accuracy: 0.7533, Val Loss: 1.2415, Val Accuracy: 0.6741 Epoch 5044/10000, Train Loss: 1.1648, Train Accuracy: 0.7489, Val Loss: 1.2414, Val Accuracy: 0.6741 Epoch 5045/10000, Train Loss: 1.1573, Train Accuracy: 0.7545, Val Loss: 1.2414, Val Accuracy: 0.6741 Epoch 5046/10000, Train Loss: 1.1682, Train Accuracy: 0.7478, Val Loss: 1.2415, Val Accuracy: 0.6741 Epoch 5047/10000, Train Loss: 1.1714, Train Accuracy: 0.7366, Val Loss: 1.2414, Val Accuracy: 0.6741 Epoch 5048/10000, Train Loss: 1.1734, Train Accuracy: 0.7489, Val Loss: 1.2416, Val Accuracy: 0.6741 Epoch 5049/10000, Train Loss: 1.1766, Train Accuracy: 0.7310, Val Loss: 1.2414, Val Accuracy: 0.6741 Epoch 5050/10000, Train Loss: 1.1609, Train Accuracy: 0.7679, Val Loss: 1.2414, Val Accuracy: 0.6741 Epoch 5051/10000, Train Loss: 1.1627, Train Accuracy: 0.7533, Val Loss: 1.2410, Val Accuracy: 0.6741 Epoch 5052/10000, Train Loss: 1.1678, Train Accuracy: 0.7500, Val Loss: 1.2409, Val Accuracy: 0.6786 Epoch 5053/10000, Train Loss: 1.1703, Train Accuracy: 0.7533, Val Loss: 1.2410, Val Accuracy: 0.6786 Epoch 5054/10000, Train Loss: 1.1432, Train Accuracy: 0.7712, Val Loss: 1.2412, Val Accuracy: 0.6786 Epoch 5055/10000, Train Loss: 1.1652, Train Accuracy: 0.7467, Val Loss: 1.2409, Val Accuracy: 0.6786 Epoch 5056/10000, Train Loss: 1.1614, Train Accuracy: 0.7545, Val Loss: 1.2409, Val Accuracy: 0.6786 Epoch 5057/10000, Train Loss: 1.1537, Train Accuracy: 0.7556, Val Loss: 1.2409, Val Accuracy: 0.6830 Epoch 5058/10000, Train Loss: 1.1625, Train Accuracy: 0.7556, Val Loss: 1.2408, Val Accuracy: 0.6830 Epoch 5059/10000, Train Loss: 1.1633, Train Accuracy: 0.7467, Val Loss: 1.2407, Val Accuracy: 0.6830 Epoch 5060/10000, Train Loss: 1.1606, Train Accuracy: 0.7667, Val Loss: 1.2408, Val Accuracy: 0.6830 Epoch 5061/10000, Train Loss: 1.1669, Train Accuracy: 0.7411, Val Loss: 1.2407, Val Accuracy: 0.6830 Epoch 5062/10000, Train Loss: 1.1541, Train Accuracy: 0.7467, Val Loss: 1.2407, Val Accuracy: 0.6786 Epoch 5063/10000, Train Loss: 1.1681, Train Accuracy: 0.7411, Val Loss: 1.2407, Val Accuracy: 0.6830 Epoch 5064/10000, Train Loss: 1.1635, Train Accuracy: 0.7522, Val Loss: 1.2407, Val Accuracy: 0.6786 Epoch 5065/10000, Train Loss: 1.1595, Train Accuracy: 0.7533, Val Loss: 1.2405, Val Accuracy: 0.6741 Epoch 5066/10000, Train Loss: 1.1710, Train Accuracy: 0.7411, Val Loss: 1.2405, Val Accuracy: 0.6741 Epoch 5067/10000, Train Loss: 1.1651, Train Accuracy: 0.7589, Val Loss: 1.2404, Val Accuracy: 0.6741 Epoch 5068/10000, Train Loss: 1.1498, Train Accuracy: 0.7779, Val Loss: 1.2405, Val Accuracy: 0.6741 Epoch 5069/10000, Train Loss: 1.1650, Train Accuracy: 0.7478, Val Loss: 1.2404, Val Accuracy: 0.6741 Epoch 5070/10000, Train Loss: 1.1632, Train Accuracy: 0.7489, Val Loss: 1.2403, Val Accuracy: 0.6741 Epoch 5071/10000, Train Loss: 1.1712, Train Accuracy: 0.7545, Val Loss: 1.2401, Val Accuracy: 0.6741 Epoch 5072/10000, Train Loss: 1.1703, Train Accuracy: 0.7411, Val Loss: 1.2401, Val Accuracy: 0.6741 Epoch 5073/10000, Train Loss: 1.1458, Train Accuracy: 0.7768, Val Loss: 1.2401, Val Accuracy: 0.6741 Epoch 5074/10000, Train Loss: 1.1631, Train Accuracy: 0.7545, Val Loss: 1.2401, Val Accuracy: 0.6741 Epoch 5075/10000, Train Loss: 1.1614, Train Accuracy: 0.7500, Val Loss: 1.2400, Val Accuracy: 0.6741 Epoch 5076/10000, Train Loss: 1.1650, Train Accuracy: 0.7556, Val Loss: 1.2401, Val Accuracy: 0.6786 Epoch 5077/10000, Train Loss: 1.1647, Train Accuracy: 0.7533, Val Loss: 1.2400, Val Accuracy: 0.6786 Epoch 5078/10000, Train Loss: 1.1593, Train Accuracy: 0.7489, Val Loss: 1.2400, Val Accuracy: 0.6786 Epoch 5079/10000, Train Loss: 1.1528, Train Accuracy: 0.7679, Val Loss: 1.2399, Val Accuracy: 0.6786 Epoch 5080/10000, Train Loss: 1.1571, Train Accuracy: 0.7656, Val Loss: 1.2401, Val Accuracy: 0.6786 Epoch 5081/10000, Train Loss: 1.1554, Train Accuracy: 0.7600, Val Loss: 1.2400, Val Accuracy: 0.6786 Epoch 5082/10000, Train Loss: 1.1537, Train Accuracy: 0.7556, Val Loss: 1.2400, Val Accuracy: 0.6786 Epoch 5083/10000, Train Loss: 1.1667, Train Accuracy: 0.7433, Val Loss: 1.2399, Val Accuracy: 0.6786 Epoch 5084/10000, Train Loss: 1.1601, Train Accuracy: 0.7545, Val Loss: 1.2398, Val Accuracy: 0.6741 Epoch 5085/10000, Train Loss: 1.1581, Train Accuracy: 0.7679, Val Loss: 1.2396, Val Accuracy: 0.6741 Epoch 5086/10000, Train Loss: 1.1598, Train Accuracy: 0.7478, Val Loss: 1.2397, Val Accuracy: 0.6741 Epoch 5087/10000, Train Loss: 1.1688, Train Accuracy: 0.7556, Val Loss: 1.2396, Val Accuracy: 0.6786 Epoch 5088/10000, Train Loss: 1.1581, Train Accuracy: 0.7600, Val Loss: 1.2396, Val Accuracy: 0.6786 Epoch 5089/10000, Train Loss: 1.1523, Train Accuracy: 0.7690, Val Loss: 1.2397, Val Accuracy: 0.6786 Epoch 5090/10000, Train Loss: 1.1583, Train Accuracy: 0.7623, Val Loss: 1.2396, Val Accuracy: 0.6786 Epoch 5091/10000, Train Loss: 1.1581, Train Accuracy: 0.7545, Val Loss: 1.2398, Val Accuracy: 0.6786 Epoch 5092/10000, Train Loss: 1.1580, Train Accuracy: 0.7679, Val Loss: 1.2394, Val Accuracy: 0.6786 Epoch 5093/10000, Train Loss: 1.1599, Train Accuracy: 0.7578, Val Loss: 1.2394, Val Accuracy: 0.6786 Epoch 5094/10000, Train Loss: 1.1618, Train Accuracy: 0.7500, Val Loss: 1.2393, Val Accuracy: 0.6786 Epoch 5095/10000, Train Loss: 1.1632, Train Accuracy: 0.7478, Val Loss: 1.2390, Val Accuracy: 0.6786 Epoch 5096/10000, Train Loss: 1.1690, Train Accuracy: 0.7433, Val Loss: 1.2391, Val Accuracy: 0.6786 Epoch 5097/10000, Train Loss: 1.1499, Train Accuracy: 0.7701, Val Loss: 1.2392, Val Accuracy: 0.6741 Epoch 5098/10000, Train Loss: 1.1532, Train Accuracy: 0.7589, Val Loss: 1.2390, Val Accuracy: 0.6741 Epoch 5099/10000, Train Loss: 1.1596, Train Accuracy: 0.7589, Val Loss: 1.2389, Val Accuracy: 0.6741 Epoch 5100/10000, Train Loss: 1.1485, Train Accuracy: 0.7690, Val Loss: 1.2390, Val Accuracy: 0.6741 Epoch 5101/10000, Train Loss: 1.1610, Train Accuracy: 0.7545, Val Loss: 1.2388, Val Accuracy: 0.6786 Epoch 5102/10000, Train Loss: 1.1564, Train Accuracy: 0.7545, Val Loss: 1.2388, Val Accuracy: 0.6786 Epoch 5103/10000, Train Loss: 1.1467, Train Accuracy: 0.7779, Val Loss: 1.2387, Val Accuracy: 0.6786 Epoch 5104/10000, Train Loss: 1.1621, Train Accuracy: 0.7600, Val Loss: 1.2386, Val Accuracy: 0.6786 Epoch 5105/10000, Train Loss: 1.1539, Train Accuracy: 0.7634, Val Loss: 1.2387, Val Accuracy: 0.6741 Epoch 5106/10000, Train Loss: 1.1683, Train Accuracy: 0.7467, Val Loss: 1.2388, Val Accuracy: 0.6741 Epoch 5107/10000, Train Loss: 1.1641, Train Accuracy: 0.7500, Val Loss: 1.2387, Val Accuracy: 0.6741 Epoch 5108/10000, Train Loss: 1.1602, Train Accuracy: 0.7600, Val Loss: 1.2387, Val Accuracy: 0.6741 Epoch 5109/10000, Train Loss: 1.1470, Train Accuracy: 0.7667, Val Loss: 1.2386, Val Accuracy: 0.6741 Epoch 5110/10000, Train Loss: 1.1614, Train Accuracy: 0.7623, Val Loss: 1.2387, Val Accuracy: 0.6786 Epoch 5111/10000, Train Loss: 1.1644, Train Accuracy: 0.7455, Val Loss: 1.2386, Val Accuracy: 0.6786 Epoch 5112/10000, Train Loss: 1.1642, Train Accuracy: 0.7478, Val Loss: 1.2385, Val Accuracy: 0.6786 Epoch 5113/10000, Train Loss: 1.1484, Train Accuracy: 0.7779, Val Loss: 1.2386, Val Accuracy: 0.6786 Epoch 5114/10000, Train Loss: 1.1524, Train Accuracy: 0.7623, Val Loss: 1.2386, Val Accuracy: 0.6786 Epoch 5115/10000, Train Loss: 1.1629, Train Accuracy: 0.7600, Val Loss: 1.2385, Val Accuracy: 0.6786 Epoch 5116/10000, Train Loss: 1.1435, Train Accuracy: 0.7701, Val Loss: 1.2387, Val Accuracy: 0.6786 Epoch 5117/10000, Train Loss: 1.1650, Train Accuracy: 0.7612, Val Loss: 1.2386, Val Accuracy: 0.6786 Epoch 5118/10000, Train Loss: 1.1544, Train Accuracy: 0.7667, Val Loss: 1.2386, Val Accuracy: 0.6786 Epoch 5119/10000, Train Loss: 1.1611, Train Accuracy: 0.7634, Val Loss: 1.2388, Val Accuracy: 0.6786 Epoch 5120/10000, Train Loss: 1.1534, Train Accuracy: 0.7656, Val Loss: 1.2385, Val Accuracy: 0.6830 Epoch 5121/10000, Train Loss: 1.1617, Train Accuracy: 0.7533, Val Loss: 1.2384, Val Accuracy: 0.6830 Epoch 5122/10000, Train Loss: 1.1578, Train Accuracy: 0.7533, Val Loss: 1.2383, Val Accuracy: 0.6786 Epoch 5123/10000, Train Loss: 1.1570, Train Accuracy: 0.7545, Val Loss: 1.2382, Val Accuracy: 0.6830 Epoch 5124/10000, Train Loss: 1.1566, Train Accuracy: 0.7679, Val Loss: 1.2381, Val Accuracy: 0.6830 Epoch 5125/10000, Train Loss: 1.1569, Train Accuracy: 0.7533, Val Loss: 1.2380, Val Accuracy: 0.6786 Epoch 5126/10000, Train Loss: 1.1555, Train Accuracy: 0.7556, Val Loss: 1.2379, Val Accuracy: 0.6830 Epoch 5127/10000, Train Loss: 1.1608, Train Accuracy: 0.7489, Val Loss: 1.2380, Val Accuracy: 0.6830 Epoch 5128/10000, Train Loss: 1.1611, Train Accuracy: 0.7511, Val Loss: 1.2380, Val Accuracy: 0.6830 Epoch 5129/10000, Train Loss: 1.1615, Train Accuracy: 0.7556, Val Loss: 1.2382, Val Accuracy: 0.6786 Epoch 5130/10000, Train Loss: 1.1598, Train Accuracy: 0.7612, Val Loss: 1.2381, Val Accuracy: 0.6786 Epoch 5131/10000, Train Loss: 1.1492, Train Accuracy: 0.7656, Val Loss: 1.2380, Val Accuracy: 0.6741 Epoch 5132/10000, Train Loss: 1.1494, Train Accuracy: 0.7634, Val Loss: 1.2381, Val Accuracy: 0.6741 Epoch 5133/10000, Train Loss: 1.1589, Train Accuracy: 0.7600, Val Loss: 1.2381, Val Accuracy: 0.6696 Epoch 5134/10000, Train Loss: 1.1538, Train Accuracy: 0.7634, Val Loss: 1.2382, Val Accuracy: 0.6696 Epoch 5135/10000, Train Loss: 1.1578, Train Accuracy: 0.7589, Val Loss: 1.2382, Val Accuracy: 0.6696 Epoch 5136/10000, Train Loss: 1.1544, Train Accuracy: 0.7623, Val Loss: 1.2380, Val Accuracy: 0.6696 Epoch 5137/10000, Train Loss: 1.1531, Train Accuracy: 0.7667, Val Loss: 1.2379, Val Accuracy: 0.6741 Epoch 5138/10000, Train Loss: 1.1584, Train Accuracy: 0.7623, Val Loss: 1.2378, Val Accuracy: 0.6741 Epoch 5139/10000, Train Loss: 1.1596, Train Accuracy: 0.7500, Val Loss: 1.2379, Val Accuracy: 0.6741 Epoch 5140/10000, Train Loss: 1.1598, Train Accuracy: 0.7578, Val Loss: 1.2378, Val Accuracy: 0.6786 Epoch 5141/10000, Train Loss: 1.1640, Train Accuracy: 0.7545, Val Loss: 1.2378, Val Accuracy: 0.6741 Epoch 5142/10000, Train Loss: 1.1522, Train Accuracy: 0.7746, Val Loss: 1.2378, Val Accuracy: 0.6786 Epoch 5143/10000, Train Loss: 1.1569, Train Accuracy: 0.7667, Val Loss: 1.2376, Val Accuracy: 0.6786 Epoch 5144/10000, Train Loss: 1.1560, Train Accuracy: 0.7545, Val Loss: 1.2376, Val Accuracy: 0.6786 Epoch 5145/10000, Train Loss: 1.1601, Train Accuracy: 0.7556, Val Loss: 1.2374, Val Accuracy: 0.6830 Epoch 5146/10000, Train Loss: 1.1629, Train Accuracy: 0.7522, Val Loss: 1.2372, Val Accuracy: 0.6830 Epoch 5147/10000, Train Loss: 1.1543, Train Accuracy: 0.7612, Val Loss: 1.2370, Val Accuracy: 0.6786 Epoch 5148/10000, Train Loss: 1.1681, Train Accuracy: 0.7388, Val Loss: 1.2373, Val Accuracy: 0.6741 Epoch 5149/10000, Train Loss: 1.1565, Train Accuracy: 0.7600, Val Loss: 1.2373, Val Accuracy: 0.6786 Epoch 5150/10000, Train Loss: 1.1666, Train Accuracy: 0.7444, Val Loss: 1.2372, Val Accuracy: 0.6830 Epoch 5151/10000, Train Loss: 1.1587, Train Accuracy: 0.7656, Val Loss: 1.2370, Val Accuracy: 0.6830 Epoch 5152/10000, Train Loss: 1.1610, Train Accuracy: 0.7500, Val Loss: 1.2372, Val Accuracy: 0.6830 Epoch 5153/10000, Train Loss: 1.1588, Train Accuracy: 0.7556, Val Loss: 1.2374, Val Accuracy: 0.6830 Epoch 5154/10000, Train Loss: 1.1589, Train Accuracy: 0.7545, Val Loss: 1.2374, Val Accuracy: 0.6830 Epoch 5155/10000, Train Loss: 1.1648, Train Accuracy: 0.7522, Val Loss: 1.2373, Val Accuracy: 0.6830 Epoch 5156/10000, Train Loss: 1.1638, Train Accuracy: 0.7489, Val Loss: 1.2372, Val Accuracy: 0.6741 Epoch 5157/10000, Train Loss: 1.1575, Train Accuracy: 0.7467, Val Loss: 1.2373, Val Accuracy: 0.6830 Epoch 5158/10000, Train Loss: 1.1663, Train Accuracy: 0.7455, Val Loss: 1.2373, Val Accuracy: 0.6830 Epoch 5159/10000, Train Loss: 1.1529, Train Accuracy: 0.7623, Val Loss: 1.2370, Val Accuracy: 0.6830 Epoch 5160/10000, Train Loss: 1.1655, Train Accuracy: 0.7444, Val Loss: 1.2370, Val Accuracy: 0.6875 Epoch 5161/10000, Train Loss: 1.1673, Train Accuracy: 0.7433, Val Loss: 1.2370, Val Accuracy: 0.6830 Epoch 5162/10000, Train Loss: 1.1650, Train Accuracy: 0.7511, Val Loss: 1.2369, Val Accuracy: 0.6830 Epoch 5163/10000, Train Loss: 1.1474, Train Accuracy: 0.7757, Val Loss: 1.2370, Val Accuracy: 0.6830 Epoch 5164/10000, Train Loss: 1.1657, Train Accuracy: 0.7556, Val Loss: 1.2368, Val Accuracy: 0.6830 Epoch 5165/10000, Train Loss: 1.1599, Train Accuracy: 0.7589, Val Loss: 1.2368, Val Accuracy: 0.6830 Epoch 5166/10000, Train Loss: 1.1509, Train Accuracy: 0.7656, Val Loss: 1.2364, Val Accuracy: 0.6830 Epoch 5167/10000, Train Loss: 1.1626, Train Accuracy: 0.7545, Val Loss: 1.2365, Val Accuracy: 0.6830 Epoch 5168/10000, Train Loss: 1.1489, Train Accuracy: 0.7589, Val Loss: 1.2365, Val Accuracy: 0.6830 Epoch 5169/10000, Train Loss: 1.1505, Train Accuracy: 0.7712, Val Loss: 1.2365, Val Accuracy: 0.6830 Epoch 5170/10000, Train Loss: 1.1589, Train Accuracy: 0.7600, Val Loss: 1.2366, Val Accuracy: 0.6830 Epoch 5171/10000, Train Loss: 1.1546, Train Accuracy: 0.7600, Val Loss: 1.2367, Val Accuracy: 0.6830 Epoch 5172/10000, Train Loss: 1.1626, Train Accuracy: 0.7500, Val Loss: 1.2367, Val Accuracy: 0.6830 Epoch 5173/10000, Train Loss: 1.1591, Train Accuracy: 0.7578, Val Loss: 1.2366, Val Accuracy: 0.6875 Epoch 5174/10000, Train Loss: 1.1553, Train Accuracy: 0.7589, Val Loss: 1.2365, Val Accuracy: 0.6830 Epoch 5175/10000, Train Loss: 1.1611, Train Accuracy: 0.7511, Val Loss: 1.2366, Val Accuracy: 0.6830 Epoch 5176/10000, Train Loss: 1.1768, Train Accuracy: 0.7333, Val Loss: 1.2367, Val Accuracy: 0.6830 Epoch 5177/10000, Train Loss: 1.1635, Train Accuracy: 0.7567, Val Loss: 1.2365, Val Accuracy: 0.6830 Epoch 5178/10000, Train Loss: 1.1483, Train Accuracy: 0.7667, Val Loss: 1.2362, Val Accuracy: 0.6830 Epoch 5179/10000, Train Loss: 1.1551, Train Accuracy: 0.7623, Val Loss: 1.2362, Val Accuracy: 0.6830 Epoch 5180/10000, Train Loss: 1.1420, Train Accuracy: 0.7768, Val Loss: 1.2363, Val Accuracy: 0.6830 Epoch 5181/10000, Train Loss: 1.1517, Train Accuracy: 0.7634, Val Loss: 1.2362, Val Accuracy: 0.6830 Epoch 5182/10000, Train Loss: 1.1573, Train Accuracy: 0.7589, Val Loss: 1.2361, Val Accuracy: 0.6830 Epoch 5183/10000, Train Loss: 1.1532, Train Accuracy: 0.7645, Val Loss: 1.2362, Val Accuracy: 0.6830 Epoch 5184/10000, Train Loss: 1.1436, Train Accuracy: 0.7679, Val Loss: 1.2361, Val Accuracy: 0.6830 Epoch 5185/10000, Train Loss: 1.1628, Train Accuracy: 0.7522, Val Loss: 1.2360, Val Accuracy: 0.6830 Epoch 5186/10000, Train Loss: 1.1566, Train Accuracy: 0.7545, Val Loss: 1.2360, Val Accuracy: 0.6830 Epoch 5187/10000, Train Loss: 1.1598, Train Accuracy: 0.7600, Val Loss: 1.2361, Val Accuracy: 0.6830 Epoch 5188/10000, Train Loss: 1.1492, Train Accuracy: 0.7589, Val Loss: 1.2360, Val Accuracy: 0.6830 Epoch 5189/10000, Train Loss: 1.1531, Train Accuracy: 0.7578, Val Loss: 1.2360, Val Accuracy: 0.6830 Epoch 5190/10000, Train Loss: 1.1540, Train Accuracy: 0.7567, Val Loss: 1.2358, Val Accuracy: 0.6830 Epoch 5191/10000, Train Loss: 1.1711, Train Accuracy: 0.7377, Val Loss: 1.2357, Val Accuracy: 0.6786 Epoch 5192/10000, Train Loss: 1.1613, Train Accuracy: 0.7623, Val Loss: 1.2357, Val Accuracy: 0.6786 Epoch 5193/10000, Train Loss: 1.1453, Train Accuracy: 0.7779, Val Loss: 1.2355, Val Accuracy: 0.6786 Epoch 5194/10000, Train Loss: 1.1539, Train Accuracy: 0.7645, Val Loss: 1.2354, Val Accuracy: 0.6786 Epoch 5195/10000, Train Loss: 1.1468, Train Accuracy: 0.7779, Val Loss: 1.2352, Val Accuracy: 0.6786 Epoch 5196/10000, Train Loss: 1.1536, Train Accuracy: 0.7667, Val Loss: 1.2354, Val Accuracy: 0.6741 Epoch 5197/10000, Train Loss: 1.1521, Train Accuracy: 0.7701, Val Loss: 1.2354, Val Accuracy: 0.6741 Epoch 5198/10000, Train Loss: 1.1615, Train Accuracy: 0.7500, Val Loss: 1.2353, Val Accuracy: 0.6786 Epoch 5199/10000, Train Loss: 1.1540, Train Accuracy: 0.7667, Val Loss: 1.2353, Val Accuracy: 0.6786 Epoch 5200/10000, Train Loss: 1.1641, Train Accuracy: 0.7578, Val Loss: 1.2354, Val Accuracy: 0.6786 Epoch 5201/10000, Train Loss: 1.1611, Train Accuracy: 0.7589, Val Loss: 1.2353, Val Accuracy: 0.6830 Epoch 5202/10000, Train Loss: 1.1530, Train Accuracy: 0.7634, Val Loss: 1.2352, Val Accuracy: 0.6786 Epoch 5203/10000, Train Loss: 1.1559, Train Accuracy: 0.7511, Val Loss: 1.2353, Val Accuracy: 0.6830 Epoch 5204/10000, Train Loss: 1.1432, Train Accuracy: 0.7746, Val Loss: 1.2353, Val Accuracy: 0.6741 Epoch 5205/10000, Train Loss: 1.1660, Train Accuracy: 0.7467, Val Loss: 1.2353, Val Accuracy: 0.6786 Epoch 5206/10000, Train Loss: 1.1643, Train Accuracy: 0.7489, Val Loss: 1.2354, Val Accuracy: 0.6786 Epoch 5207/10000, Train Loss: 1.1493, Train Accuracy: 0.7712, Val Loss: 1.2353, Val Accuracy: 0.6786 Epoch 5208/10000, Train Loss: 1.1673, Train Accuracy: 0.7366, Val Loss: 1.2353, Val Accuracy: 0.6786 Epoch 5209/10000, Train Loss: 1.1510, Train Accuracy: 0.7589, Val Loss: 1.2353, Val Accuracy: 0.6786 Epoch 5210/10000, Train Loss: 1.1507, Train Accuracy: 0.7533, Val Loss: 1.2351, Val Accuracy: 0.6830 Epoch 5211/10000, Train Loss: 1.1566, Train Accuracy: 0.7612, Val Loss: 1.2351, Val Accuracy: 0.6875 Epoch 5212/10000, Train Loss: 1.1565, Train Accuracy: 0.7600, Val Loss: 1.2351, Val Accuracy: 0.6830 Epoch 5213/10000, Train Loss: 1.1487, Train Accuracy: 0.7746, Val Loss: 1.2350, Val Accuracy: 0.6830 Epoch 5214/10000, Train Loss: 1.1546, Train Accuracy: 0.7634, Val Loss: 1.2351, Val Accuracy: 0.6875 Epoch 5215/10000, Train Loss: 1.1508, Train Accuracy: 0.7690, Val Loss: 1.2347, Val Accuracy: 0.6875 Epoch 5216/10000, Train Loss: 1.1655, Train Accuracy: 0.7533, Val Loss: 1.2348, Val Accuracy: 0.6830 Epoch 5217/10000, Train Loss: 1.1412, Train Accuracy: 0.7779, Val Loss: 1.2347, Val Accuracy: 0.6830 Epoch 5218/10000, Train Loss: 1.1505, Train Accuracy: 0.7623, Val Loss: 1.2346, Val Accuracy: 0.6875 Epoch 5219/10000, Train Loss: 1.1486, Train Accuracy: 0.7623, Val Loss: 1.2344, Val Accuracy: 0.6875 Epoch 5220/10000, Train Loss: 1.1524, Train Accuracy: 0.7645, Val Loss: 1.2345, Val Accuracy: 0.6920 Epoch 5221/10000, Train Loss: 1.1620, Train Accuracy: 0.7489, Val Loss: 1.2343, Val Accuracy: 0.6875 Epoch 5222/10000, Train Loss: 1.1562, Train Accuracy: 0.7701, Val Loss: 1.2341, Val Accuracy: 0.6920 Epoch 5223/10000, Train Loss: 1.1553, Train Accuracy: 0.7545, Val Loss: 1.2341, Val Accuracy: 0.6875 Epoch 5224/10000, Train Loss: 1.1507, Train Accuracy: 0.7656, Val Loss: 1.2340, Val Accuracy: 0.6875 Epoch 5225/10000, Train Loss: 1.1565, Train Accuracy: 0.7467, Val Loss: 1.2338, Val Accuracy: 0.6875 Epoch 5226/10000, Train Loss: 1.1464, Train Accuracy: 0.7690, Val Loss: 1.2338, Val Accuracy: 0.6875 Epoch 5227/10000, Train Loss: 1.1534, Train Accuracy: 0.7645, Val Loss: 1.2336, Val Accuracy: 0.6875 Epoch 5228/10000, Train Loss: 1.1454, Train Accuracy: 0.7779, Val Loss: 1.2333, Val Accuracy: 0.6875 Epoch 5229/10000, Train Loss: 1.1630, Train Accuracy: 0.7422, Val Loss: 1.2333, Val Accuracy: 0.6875 Epoch 5230/10000, Train Loss: 1.1600, Train Accuracy: 0.7578, Val Loss: 1.2335, Val Accuracy: 0.6875 Epoch 5231/10000, Train Loss: 1.1550, Train Accuracy: 0.7645, Val Loss: 1.2336, Val Accuracy: 0.6875 Epoch 5232/10000, Train Loss: 1.1657, Train Accuracy: 0.7500, Val Loss: 1.2338, Val Accuracy: 0.6875 Epoch 5233/10000, Train Loss: 1.1551, Train Accuracy: 0.7567, Val Loss: 1.2337, Val Accuracy: 0.6875 Epoch 5234/10000, Train Loss: 1.1526, Train Accuracy: 0.7679, Val Loss: 1.2336, Val Accuracy: 0.6830 Epoch 5235/10000, Train Loss: 1.1536, Train Accuracy: 0.7690, Val Loss: 1.2334, Val Accuracy: 0.6875 Epoch 5236/10000, Train Loss: 1.1624, Train Accuracy: 0.7500, Val Loss: 1.2332, Val Accuracy: 0.6830 Epoch 5237/10000, Train Loss: 1.1513, Train Accuracy: 0.7589, Val Loss: 1.2331, Val Accuracy: 0.6830 Epoch 5238/10000, Train Loss: 1.1552, Train Accuracy: 0.7679, Val Loss: 1.2333, Val Accuracy: 0.6830 Epoch 5239/10000, Train Loss: 1.1506, Train Accuracy: 0.7656, Val Loss: 1.2331, Val Accuracy: 0.6830 Epoch 5240/10000, Train Loss: 1.1522, Train Accuracy: 0.7679, Val Loss: 1.2333, Val Accuracy: 0.6830 Epoch 5241/10000, Train Loss: 1.1437, Train Accuracy: 0.7746, Val Loss: 1.2331, Val Accuracy: 0.6830 Epoch 5242/10000, Train Loss: 1.1650, Train Accuracy: 0.7511, Val Loss: 1.2330, Val Accuracy: 0.6830 Epoch 5243/10000, Train Loss: 1.1549, Train Accuracy: 0.7679, Val Loss: 1.2329, Val Accuracy: 0.6830 Epoch 5244/10000, Train Loss: 1.1521, Train Accuracy: 0.7768, Val Loss: 1.2329, Val Accuracy: 0.6875 Epoch 5245/10000, Train Loss: 1.1467, Train Accuracy: 0.7812, Val Loss: 1.2328, Val Accuracy: 0.6830 Epoch 5246/10000, Train Loss: 1.1463, Train Accuracy: 0.7679, Val Loss: 1.2329, Val Accuracy: 0.6830 Epoch 5247/10000, Train Loss: 1.1608, Train Accuracy: 0.7567, Val Loss: 1.2328, Val Accuracy: 0.6830 Epoch 5248/10000, Train Loss: 1.1492, Train Accuracy: 0.7556, Val Loss: 1.2329, Val Accuracy: 0.6830 Epoch 5249/10000, Train Loss: 1.1408, Train Accuracy: 0.7768, Val Loss: 1.2331, Val Accuracy: 0.6830 Epoch 5250/10000, Train Loss: 1.1423, Train Accuracy: 0.7734, Val Loss: 1.2330, Val Accuracy: 0.6830 Epoch 5251/10000, Train Loss: 1.1495, Train Accuracy: 0.7656, Val Loss: 1.2328, Val Accuracy: 0.6830 Epoch 5252/10000, Train Loss: 1.1521, Train Accuracy: 0.7612, Val Loss: 1.2329, Val Accuracy: 0.6830 Epoch 5253/10000, Train Loss: 1.1553, Train Accuracy: 0.7589, Val Loss: 1.2325, Val Accuracy: 0.6830 Epoch 5254/10000, Train Loss: 1.1462, Train Accuracy: 0.7746, Val Loss: 1.2324, Val Accuracy: 0.6786 Epoch 5255/10000, Train Loss: 1.1398, Train Accuracy: 0.7757, Val Loss: 1.2324, Val Accuracy: 0.6786 Epoch 5256/10000, Train Loss: 1.1519, Train Accuracy: 0.7690, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5257/10000, Train Loss: 1.1529, Train Accuracy: 0.7712, Val Loss: 1.2324, Val Accuracy: 0.6830 Epoch 5258/10000, Train Loss: 1.1429, Train Accuracy: 0.7667, Val Loss: 1.2324, Val Accuracy: 0.6830 Epoch 5259/10000, Train Loss: 1.1507, Train Accuracy: 0.7667, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5260/10000, Train Loss: 1.1621, Train Accuracy: 0.7511, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5261/10000, Train Loss: 1.1606, Train Accuracy: 0.7556, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5262/10000, Train Loss: 1.1410, Train Accuracy: 0.7667, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5263/10000, Train Loss: 1.1509, Train Accuracy: 0.7589, Val Loss: 1.2324, Val Accuracy: 0.6830 Epoch 5264/10000, Train Loss: 1.1483, Train Accuracy: 0.7701, Val Loss: 1.2322, Val Accuracy: 0.6786 Epoch 5265/10000, Train Loss: 1.1538, Train Accuracy: 0.7567, Val Loss: 1.2324, Val Accuracy: 0.6786 Epoch 5266/10000, Train Loss: 1.1541, Train Accuracy: 0.7645, Val Loss: 1.2323, Val Accuracy: 0.6786 Epoch 5267/10000, Train Loss: 1.1558, Train Accuracy: 0.7690, Val Loss: 1.2322, Val Accuracy: 0.6830 Epoch 5268/10000, Train Loss: 1.1465, Train Accuracy: 0.7746, Val Loss: 1.2322, Val Accuracy: 0.6830 Epoch 5269/10000, Train Loss: 1.1417, Train Accuracy: 0.7690, Val Loss: 1.2322, Val Accuracy: 0.6830 Epoch 5270/10000, Train Loss: 1.1550, Train Accuracy: 0.7500, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5271/10000, Train Loss: 1.1415, Train Accuracy: 0.7734, Val Loss: 1.2323, Val Accuracy: 0.6830 Epoch 5272/10000, Train Loss: 1.1535, Train Accuracy: 0.7600, Val Loss: 1.2321, Val Accuracy: 0.6830 Epoch 5273/10000, Train Loss: 1.1458, Train Accuracy: 0.7690, Val Loss: 1.2318, Val Accuracy: 0.6830 Epoch 5274/10000, Train Loss: 1.1455, Train Accuracy: 0.7645, Val Loss: 1.2317, Val Accuracy: 0.6830 Epoch 5275/10000, Train Loss: 1.1420, Train Accuracy: 0.7857, Val Loss: 1.2314, Val Accuracy: 0.6830 Epoch 5276/10000, Train Loss: 1.1515, Train Accuracy: 0.7634, Val Loss: 1.2314, Val Accuracy: 0.6830 Epoch 5277/10000, Train Loss: 1.1569, Train Accuracy: 0.7612, Val Loss: 1.2317, Val Accuracy: 0.6830 Epoch 5278/10000, Train Loss: 1.1429, Train Accuracy: 0.7679, Val Loss: 1.2316, Val Accuracy: 0.6830 Epoch 5279/10000, Train Loss: 1.1467, Train Accuracy: 0.7757, Val Loss: 1.2314, Val Accuracy: 0.6830 Epoch 5280/10000, Train Loss: 1.1453, Train Accuracy: 0.7701, Val Loss: 1.2313, Val Accuracy: 0.6830 Epoch 5281/10000, Train Loss: 1.1567, Train Accuracy: 0.7667, Val Loss: 1.2314, Val Accuracy: 0.6830 Epoch 5282/10000, Train Loss: 1.1408, Train Accuracy: 0.7835, Val Loss: 1.2313, Val Accuracy: 0.6830 Epoch 5283/10000, Train Loss: 1.1526, Train Accuracy: 0.7634, Val Loss: 1.2313, Val Accuracy: 0.6830 Epoch 5284/10000, Train Loss: 1.1471, Train Accuracy: 0.7790, Val Loss: 1.2314, Val Accuracy: 0.6786 Epoch 5285/10000, Train Loss: 1.1653, Train Accuracy: 0.7489, Val Loss: 1.2314, Val Accuracy: 0.6830 Epoch 5286/10000, Train Loss: 1.1419, Train Accuracy: 0.7812, Val Loss: 1.2315, Val Accuracy: 0.6830 Epoch 5287/10000, Train Loss: 1.1408, Train Accuracy: 0.7746, Val Loss: 1.2317, Val Accuracy: 0.6786 Epoch 5288/10000, Train Loss: 1.1503, Train Accuracy: 0.7645, Val Loss: 1.2318, Val Accuracy: 0.6786 Epoch 5289/10000, Train Loss: 1.1467, Train Accuracy: 0.7612, Val Loss: 1.2319, Val Accuracy: 0.6786 Epoch 5290/10000, Train Loss: 1.1450, Train Accuracy: 0.7701, Val Loss: 1.2316, Val Accuracy: 0.6786 Epoch 5291/10000, Train Loss: 1.1496, Train Accuracy: 0.7723, Val Loss: 1.2315, Val Accuracy: 0.6786 Epoch 5292/10000, Train Loss: 1.1626, Train Accuracy: 0.7533, Val Loss: 1.2316, Val Accuracy: 0.6830 Epoch 5293/10000, Train Loss: 1.1433, Train Accuracy: 0.7734, Val Loss: 1.2313, Val Accuracy: 0.6830 Epoch 5294/10000, Train Loss: 1.1467, Train Accuracy: 0.7679, Val Loss: 1.2313, Val Accuracy: 0.6830 Epoch 5295/10000, Train Loss: 1.1585, Train Accuracy: 0.7545, Val Loss: 1.2312, Val Accuracy: 0.6830 Epoch 5296/10000, Train Loss: 1.1417, Train Accuracy: 0.7757, Val Loss: 1.2310, Val Accuracy: 0.6830 Epoch 5297/10000, Train Loss: 1.1509, Train Accuracy: 0.7679, Val Loss: 1.2309, Val Accuracy: 0.6875 Epoch 5298/10000, Train Loss: 1.1474, Train Accuracy: 0.7623, Val Loss: 1.2308, Val Accuracy: 0.6830 Epoch 5299/10000, Train Loss: 1.1506, Train Accuracy: 0.7679, Val Loss: 1.2306, Val Accuracy: 0.6875 Epoch 5300/10000, Train Loss: 1.1393, Train Accuracy: 0.7790, Val Loss: 1.2305, Val Accuracy: 0.6875 Epoch 5301/10000, Train Loss: 1.1627, Train Accuracy: 0.7478, Val Loss: 1.2304, Val Accuracy: 0.6875 Epoch 5302/10000, Train Loss: 1.1508, Train Accuracy: 0.7746, Val Loss: 1.2302, Val Accuracy: 0.6875 Epoch 5303/10000, Train Loss: 1.1412, Train Accuracy: 0.7801, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5304/10000, Train Loss: 1.1529, Train Accuracy: 0.7667, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5305/10000, Train Loss: 1.1412, Train Accuracy: 0.7790, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5306/10000, Train Loss: 1.1393, Train Accuracy: 0.7768, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5307/10000, Train Loss: 1.1395, Train Accuracy: 0.7779, Val Loss: 1.2298, Val Accuracy: 0.6875 Epoch 5308/10000, Train Loss: 1.1452, Train Accuracy: 0.7734, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5309/10000, Train Loss: 1.1435, Train Accuracy: 0.7757, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5310/10000, Train Loss: 1.1498, Train Accuracy: 0.7701, Val Loss: 1.2299, Val Accuracy: 0.6875 Epoch 5311/10000, Train Loss: 1.1468, Train Accuracy: 0.7801, Val Loss: 1.2301, Val Accuracy: 0.6830 Epoch 5312/10000, Train Loss: 1.1402, Train Accuracy: 0.7824, Val Loss: 1.2303, Val Accuracy: 0.6830 Epoch 5313/10000, Train Loss: 1.1551, Train Accuracy: 0.7656, Val Loss: 1.2304, Val Accuracy: 0.6830 Epoch 5314/10000, Train Loss: 1.1501, Train Accuracy: 0.7623, Val Loss: 1.2303, Val Accuracy: 0.6830 Epoch 5315/10000, Train Loss: 1.1341, Train Accuracy: 0.7846, Val Loss: 1.2302, Val Accuracy: 0.6830 Epoch 5316/10000, Train Loss: 1.1557, Train Accuracy: 0.7600, Val Loss: 1.2302, Val Accuracy: 0.6830 Epoch 5317/10000, Train Loss: 1.1486, Train Accuracy: 0.7679, Val Loss: 1.2299, Val Accuracy: 0.6830 Epoch 5318/10000, Train Loss: 1.1564, Train Accuracy: 0.7533, Val Loss: 1.2301, Val Accuracy: 0.6830 Epoch 5319/10000, Train Loss: 1.1480, Train Accuracy: 0.7645, Val Loss: 1.2298, Val Accuracy: 0.6830 Epoch 5320/10000, Train Loss: 1.1498, Train Accuracy: 0.7645, Val Loss: 1.2296, Val Accuracy: 0.6830 Epoch 5321/10000, Train Loss: 1.1554, Train Accuracy: 0.7567, Val Loss: 1.2294, Val Accuracy: 0.6875 Epoch 5322/10000, Train Loss: 1.1414, Train Accuracy: 0.7768, Val Loss: 1.2294, Val Accuracy: 0.6875 Epoch 5323/10000, Train Loss: 1.1388, Train Accuracy: 0.7734, Val Loss: 1.2293, Val Accuracy: 0.6875 Epoch 5324/10000, Train Loss: 1.1393, Train Accuracy: 0.7801, Val Loss: 1.2292, Val Accuracy: 0.6875 Epoch 5325/10000, Train Loss: 1.1450, Train Accuracy: 0.7667, Val Loss: 1.2293, Val Accuracy: 0.6830 Epoch 5326/10000, Train Loss: 1.1452, Train Accuracy: 0.7757, Val Loss: 1.2293, Val Accuracy: 0.6830 Epoch 5327/10000, Train Loss: 1.1474, Train Accuracy: 0.7623, Val Loss: 1.2294, Val Accuracy: 0.6786 Epoch 5328/10000, Train Loss: 1.1517, Train Accuracy: 0.7612, Val Loss: 1.2294, Val Accuracy: 0.6830 Epoch 5329/10000, Train Loss: 1.1459, Train Accuracy: 0.7701, Val Loss: 1.2294, Val Accuracy: 0.6786 Epoch 5330/10000, Train Loss: 1.1452, Train Accuracy: 0.7679, Val Loss: 1.2293, Val Accuracy: 0.6786 Epoch 5331/10000, Train Loss: 1.1513, Train Accuracy: 0.7522, Val Loss: 1.2294, Val Accuracy: 0.6786 Epoch 5332/10000, Train Loss: 1.1557, Train Accuracy: 0.7645, Val Loss: 1.2293, Val Accuracy: 0.6786 Epoch 5333/10000, Train Loss: 1.1495, Train Accuracy: 0.7634, Val Loss: 1.2291, Val Accuracy: 0.6786 Epoch 5334/10000, Train Loss: 1.1557, Train Accuracy: 0.7533, Val Loss: 1.2290, Val Accuracy: 0.6786 Epoch 5335/10000, Train Loss: 1.1430, Train Accuracy: 0.7779, Val Loss: 1.2289, Val Accuracy: 0.6786 Epoch 5336/10000, Train Loss: 1.1474, Train Accuracy: 0.7679, Val Loss: 1.2289, Val Accuracy: 0.6786 Epoch 5337/10000, Train Loss: 1.1519, Train Accuracy: 0.7712, Val Loss: 1.2287, Val Accuracy: 0.6786 Epoch 5338/10000, Train Loss: 1.1470, Train Accuracy: 0.7746, Val Loss: 1.2288, Val Accuracy: 0.6830 Epoch 5339/10000, Train Loss: 1.1436, Train Accuracy: 0.7768, Val Loss: 1.2286, Val Accuracy: 0.6830 Epoch 5340/10000, Train Loss: 1.1454, Train Accuracy: 0.7679, Val Loss: 1.2286, Val Accuracy: 0.6830 Epoch 5341/10000, Train Loss: 1.1578, Train Accuracy: 0.7545, Val Loss: 1.2285, Val Accuracy: 0.6830 Epoch 5342/10000, Train Loss: 1.1513, Train Accuracy: 0.7634, Val Loss: 1.2286, Val Accuracy: 0.6830 Epoch 5343/10000, Train Loss: 1.1436, Train Accuracy: 0.7723, Val Loss: 1.2286, Val Accuracy: 0.6830 Epoch 5344/10000, Train Loss: 1.1472, Train Accuracy: 0.7645, Val Loss: 1.2287, Val Accuracy: 0.6830 Epoch 5345/10000, Train Loss: 1.1486, Train Accuracy: 0.7779, Val Loss: 1.2289, Val Accuracy: 0.6786 Epoch 5346/10000, Train Loss: 1.1634, Train Accuracy: 0.7522, Val Loss: 1.2289, Val Accuracy: 0.6786 Epoch 5347/10000, Train Loss: 1.1427, Train Accuracy: 0.7746, Val Loss: 1.2288, Val Accuracy: 0.6786 Epoch 5348/10000, Train Loss: 1.1508, Train Accuracy: 0.7690, Val Loss: 1.2288, Val Accuracy: 0.6786 Epoch 5349/10000, Train Loss: 1.1522, Train Accuracy: 0.7589, Val Loss: 1.2288, Val Accuracy: 0.6786 Epoch 5350/10000, Train Loss: 1.1312, Train Accuracy: 0.7824, Val Loss: 1.2285, Val Accuracy: 0.6786 Epoch 5351/10000, Train Loss: 1.1401, Train Accuracy: 0.7768, Val Loss: 1.2285, Val Accuracy: 0.6786 Epoch 5352/10000, Train Loss: 1.1465, Train Accuracy: 0.7746, Val Loss: 1.2280, Val Accuracy: 0.6786 Epoch 5353/10000, Train Loss: 1.1430, Train Accuracy: 0.7734, Val Loss: 1.2280, Val Accuracy: 0.6786 Epoch 5354/10000, Train Loss: 1.1630, Train Accuracy: 0.7522, Val Loss: 1.2279, Val Accuracy: 0.6786 Epoch 5355/10000, Train Loss: 1.1554, Train Accuracy: 0.7567, Val Loss: 1.2281, Val Accuracy: 0.6830 Epoch 5356/10000, Train Loss: 1.1407, Train Accuracy: 0.7712, Val Loss: 1.2280, Val Accuracy: 0.6830 Epoch 5357/10000, Train Loss: 1.1501, Train Accuracy: 0.7623, Val Loss: 1.2280, Val Accuracy: 0.6830 Epoch 5358/10000, Train Loss: 1.1398, Train Accuracy: 0.7712, Val Loss: 1.2281, Val Accuracy: 0.6830 Epoch 5359/10000, Train Loss: 1.1535, Train Accuracy: 0.7634, Val Loss: 1.2279, Val Accuracy: 0.6830 Epoch 5360/10000, Train Loss: 1.1503, Train Accuracy: 0.7645, Val Loss: 1.2278, Val Accuracy: 0.6830 Epoch 5361/10000, Train Loss: 1.1476, Train Accuracy: 0.7578, Val Loss: 1.2276, Val Accuracy: 0.6830 Epoch 5362/10000, Train Loss: 1.1461, Train Accuracy: 0.7757, Val Loss: 1.2275, Val Accuracy: 0.6830 Epoch 5363/10000, Train Loss: 1.1507, Train Accuracy: 0.7701, Val Loss: 1.2277, Val Accuracy: 0.6830 Epoch 5364/10000, Train Loss: 1.1448, Train Accuracy: 0.7790, Val Loss: 1.2277, Val Accuracy: 0.6830 Epoch 5365/10000, Train Loss: 1.1440, Train Accuracy: 0.7701, Val Loss: 1.2277, Val Accuracy: 0.6830 Epoch 5366/10000, Train Loss: 1.1558, Train Accuracy: 0.7556, Val Loss: 1.2277, Val Accuracy: 0.6830 Epoch 5367/10000, Train Loss: 1.1329, Train Accuracy: 0.7857, Val Loss: 1.2277, Val Accuracy: 0.6830 Epoch 5368/10000, Train Loss: 1.1506, Train Accuracy: 0.7578, Val Loss: 1.2275, Val Accuracy: 0.6830 Epoch 5369/10000, Train Loss: 1.1466, Train Accuracy: 0.7723, Val Loss: 1.2277, Val Accuracy: 0.6786 Epoch 5370/10000, Train Loss: 1.1593, Train Accuracy: 0.7511, Val Loss: 1.2277, Val Accuracy: 0.6786 Epoch 5371/10000, Train Loss: 1.1400, Train Accuracy: 0.7790, Val Loss: 1.2276, Val Accuracy: 0.6786 Epoch 5372/10000, Train Loss: 1.1522, Train Accuracy: 0.7723, Val Loss: 1.2275, Val Accuracy: 0.6786 Epoch 5373/10000, Train Loss: 1.1471, Train Accuracy: 0.7757, Val Loss: 1.2275, Val Accuracy: 0.6786 Epoch 5374/10000, Train Loss: 1.1481, Train Accuracy: 0.7734, Val Loss: 1.2275, Val Accuracy: 0.6786 Epoch 5375/10000, Train Loss: 1.1425, Train Accuracy: 0.7746, Val Loss: 1.2274, Val Accuracy: 0.6786 Epoch 5376/10000, Train Loss: 1.1534, Train Accuracy: 0.7600, Val Loss: 1.2273, Val Accuracy: 0.6786 Epoch 5377/10000, Train Loss: 1.1523, Train Accuracy: 0.7634, Val Loss: 1.2273, Val Accuracy: 0.6786 Epoch 5378/10000, Train Loss: 1.1427, Train Accuracy: 0.7746, Val Loss: 1.2274, Val Accuracy: 0.6786 Epoch 5379/10000, Train Loss: 1.1531, Train Accuracy: 0.7667, Val Loss: 1.2275, Val Accuracy: 0.6786 Epoch 5380/10000, Train Loss: 1.1528, Train Accuracy: 0.7656, Val Loss: 1.2272, Val Accuracy: 0.6786 Epoch 5381/10000, Train Loss: 1.1377, Train Accuracy: 0.7757, Val Loss: 1.2271, Val Accuracy: 0.6786 Epoch 5382/10000, Train Loss: 1.1424, Train Accuracy: 0.7757, Val Loss: 1.2271, Val Accuracy: 0.6830 Epoch 5383/10000, Train Loss: 1.1342, Train Accuracy: 0.7790, Val Loss: 1.2269, Val Accuracy: 0.6830 Epoch 5384/10000, Train Loss: 1.1433, Train Accuracy: 0.7746, Val Loss: 1.2269, Val Accuracy: 0.6830 Epoch 5385/10000, Train Loss: 1.1449, Train Accuracy: 0.7790, Val Loss: 1.2270, Val Accuracy: 0.6830 Epoch 5386/10000, Train Loss: 1.1364, Train Accuracy: 0.7812, Val Loss: 1.2265, Val Accuracy: 0.6786 Epoch 5387/10000, Train Loss: 1.1407, Train Accuracy: 0.7757, Val Loss: 1.2264, Val Accuracy: 0.6830 Epoch 5388/10000, Train Loss: 1.1532, Train Accuracy: 0.7667, Val Loss: 1.2262, Val Accuracy: 0.6830 Epoch 5389/10000, Train Loss: 1.1459, Train Accuracy: 0.7757, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5390/10000, Train Loss: 1.1535, Train Accuracy: 0.7578, Val Loss: 1.2262, Val Accuracy: 0.6830 Epoch 5391/10000, Train Loss: 1.1584, Train Accuracy: 0.7567, Val Loss: 1.2263, Val Accuracy: 0.6875 Epoch 5392/10000, Train Loss: 1.1402, Train Accuracy: 0.7701, Val Loss: 1.2262, Val Accuracy: 0.6875 Epoch 5393/10000, Train Loss: 1.1517, Train Accuracy: 0.7589, Val Loss: 1.2262, Val Accuracy: 0.6830 Epoch 5394/10000, Train Loss: 1.1531, Train Accuracy: 0.7556, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5395/10000, Train Loss: 1.1481, Train Accuracy: 0.7645, Val Loss: 1.2258, Val Accuracy: 0.6875 Epoch 5396/10000, Train Loss: 1.1530, Train Accuracy: 0.7712, Val Loss: 1.2258, Val Accuracy: 0.6875 Epoch 5397/10000, Train Loss: 1.1431, Train Accuracy: 0.7712, Val Loss: 1.2259, Val Accuracy: 0.6875 Epoch 5398/10000, Train Loss: 1.1451, Train Accuracy: 0.7690, Val Loss: 1.2257, Val Accuracy: 0.6875 Epoch 5399/10000, Train Loss: 1.1510, Train Accuracy: 0.7578, Val Loss: 1.2258, Val Accuracy: 0.6875 Epoch 5400/10000, Train Loss: 1.1459, Train Accuracy: 0.7746, Val Loss: 1.2259, Val Accuracy: 0.6875 Epoch 5401/10000, Train Loss: 1.1381, Train Accuracy: 0.7801, Val Loss: 1.2262, Val Accuracy: 0.6875 Epoch 5402/10000, Train Loss: 1.1501, Train Accuracy: 0.7533, Val Loss: 1.2263, Val Accuracy: 0.6875 Epoch 5403/10000, Train Loss: 1.1380, Train Accuracy: 0.7734, Val Loss: 1.2263, Val Accuracy: 0.6830 Epoch 5404/10000, Train Loss: 1.1491, Train Accuracy: 0.7623, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5405/10000, Train Loss: 1.1530, Train Accuracy: 0.7623, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5406/10000, Train Loss: 1.1430, Train Accuracy: 0.7734, Val Loss: 1.2259, Val Accuracy: 0.6786 Epoch 5407/10000, Train Loss: 1.1427, Train Accuracy: 0.7701, Val Loss: 1.2260, Val Accuracy: 0.6786 Epoch 5408/10000, Train Loss: 1.1473, Train Accuracy: 0.7701, Val Loss: 1.2261, Val Accuracy: 0.6786 Epoch 5409/10000, Train Loss: 1.1431, Train Accuracy: 0.7701, Val Loss: 1.2263, Val Accuracy: 0.6786 Epoch 5410/10000, Train Loss: 1.1474, Train Accuracy: 0.7667, Val Loss: 1.2264, Val Accuracy: 0.6786 Epoch 5411/10000, Train Loss: 1.1442, Train Accuracy: 0.7768, Val Loss: 1.2263, Val Accuracy: 0.6786 Epoch 5412/10000, Train Loss: 1.1378, Train Accuracy: 0.7746, Val Loss: 1.2263, Val Accuracy: 0.6875 Epoch 5413/10000, Train Loss: 1.1519, Train Accuracy: 0.7623, Val Loss: 1.2262, Val Accuracy: 0.6875 Epoch 5414/10000, Train Loss: 1.1465, Train Accuracy: 0.7812, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5415/10000, Train Loss: 1.1534, Train Accuracy: 0.7623, Val Loss: 1.2260, Val Accuracy: 0.6875 Epoch 5416/10000, Train Loss: 1.1308, Train Accuracy: 0.7935, Val Loss: 1.2260, Val Accuracy: 0.6875 Epoch 5417/10000, Train Loss: 1.1423, Train Accuracy: 0.7734, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5418/10000, Train Loss: 1.1341, Train Accuracy: 0.7824, Val Loss: 1.2258, Val Accuracy: 0.6875 Epoch 5419/10000, Train Loss: 1.1408, Train Accuracy: 0.7790, Val Loss: 1.2260, Val Accuracy: 0.6875 Epoch 5420/10000, Train Loss: 1.1550, Train Accuracy: 0.7589, Val Loss: 1.2259, Val Accuracy: 0.6875 Epoch 5421/10000, Train Loss: 1.1325, Train Accuracy: 0.7958, Val Loss: 1.2260, Val Accuracy: 0.6875 Epoch 5422/10000, Train Loss: 1.1370, Train Accuracy: 0.7790, Val Loss: 1.2262, Val Accuracy: 0.6875 Epoch 5423/10000, Train Loss: 1.1525, Train Accuracy: 0.7656, Val Loss: 1.2260, Val Accuracy: 0.6875 Epoch 5424/10000, Train Loss: 1.1414, Train Accuracy: 0.7835, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5425/10000, Train Loss: 1.1474, Train Accuracy: 0.7723, Val Loss: 1.2259, Val Accuracy: 0.6875 Epoch 5426/10000, Train Loss: 1.1523, Train Accuracy: 0.7690, Val Loss: 1.2259, Val Accuracy: 0.6875 Epoch 5427/10000, Train Loss: 1.1484, Train Accuracy: 0.7746, Val Loss: 1.2259, Val Accuracy: 0.6830 Epoch 5428/10000, Train Loss: 1.1435, Train Accuracy: 0.7734, Val Loss: 1.2257, Val Accuracy: 0.6875 Epoch 5429/10000, Train Loss: 1.1439, Train Accuracy: 0.7812, Val Loss: 1.2259, Val Accuracy: 0.6830 Epoch 5430/10000, Train Loss: 1.1421, Train Accuracy: 0.7734, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5431/10000, Train Loss: 1.1529, Train Accuracy: 0.7556, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5432/10000, Train Loss: 1.1566, Train Accuracy: 0.7567, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5433/10000, Train Loss: 1.1493, Train Accuracy: 0.7679, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5434/10000, Train Loss: 1.1443, Train Accuracy: 0.7812, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5435/10000, Train Loss: 1.1471, Train Accuracy: 0.7712, Val Loss: 1.2262, Val Accuracy: 0.6830 Epoch 5436/10000, Train Loss: 1.1396, Train Accuracy: 0.7746, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5437/10000, Train Loss: 1.1323, Train Accuracy: 0.7801, Val Loss: 1.2262, Val Accuracy: 0.6830 Epoch 5438/10000, Train Loss: 1.1353, Train Accuracy: 0.7891, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5439/10000, Train Loss: 1.1512, Train Accuracy: 0.7667, Val Loss: 1.2264, Val Accuracy: 0.6830 Epoch 5440/10000, Train Loss: 1.1457, Train Accuracy: 0.7712, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5441/10000, Train Loss: 1.1471, Train Accuracy: 0.7656, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5442/10000, Train Loss: 1.1409, Train Accuracy: 0.7667, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5443/10000, Train Loss: 1.1355, Train Accuracy: 0.7801, Val Loss: 1.2260, Val Accuracy: 0.6830 Epoch 5444/10000, Train Loss: 1.1465, Train Accuracy: 0.7701, Val Loss: 1.2262, Val Accuracy: 0.6830 Epoch 5445/10000, Train Loss: 1.1355, Train Accuracy: 0.7768, Val Loss: 1.2261, Val Accuracy: 0.6830 Epoch 5446/10000, Train Loss: 1.1411, Train Accuracy: 0.7701, Val Loss: 1.2258, Val Accuracy: 0.6830 Epoch 5447/10000, Train Loss: 1.1444, Train Accuracy: 0.7746, Val Loss: 1.2256, Val Accuracy: 0.6830 Epoch 5448/10000, Train Loss: 1.1527, Train Accuracy: 0.7600, Val Loss: 1.2256, Val Accuracy: 0.6830 Epoch 5449/10000, Train Loss: 1.1374, Train Accuracy: 0.7757, Val Loss: 1.2257, Val Accuracy: 0.6830 Epoch 5450/10000, Train Loss: 1.1297, Train Accuracy: 0.7902, Val Loss: 1.2253, Val Accuracy: 0.6830 Epoch 5451/10000, Train Loss: 1.1485, Train Accuracy: 0.7667, Val Loss: 1.2252, Val Accuracy: 0.6830 Epoch 5452/10000, Train Loss: 1.1435, Train Accuracy: 0.7723, Val Loss: 1.2253, Val Accuracy: 0.6830 Epoch 5453/10000, Train Loss: 1.1359, Train Accuracy: 0.7835, Val Loss: 1.2252, Val Accuracy: 0.6830 Epoch 5454/10000, Train Loss: 1.1556, Train Accuracy: 0.7556, Val Loss: 1.2253, Val Accuracy: 0.6830 Epoch 5455/10000, Train Loss: 1.1407, Train Accuracy: 0.7846, Val Loss: 1.2251, Val Accuracy: 0.6875 Epoch 5456/10000, Train Loss: 1.1431, Train Accuracy: 0.7667, Val Loss: 1.2249, Val Accuracy: 0.6875 Epoch 5457/10000, Train Loss: 1.1365, Train Accuracy: 0.7879, Val Loss: 1.2250, Val Accuracy: 0.6920 Epoch 5458/10000, Train Loss: 1.1298, Train Accuracy: 0.7924, Val Loss: 1.2251, Val Accuracy: 0.6920 Epoch 5459/10000, Train Loss: 1.1509, Train Accuracy: 0.7645, Val Loss: 1.2248, Val Accuracy: 0.6920 Epoch 5460/10000, Train Loss: 1.1450, Train Accuracy: 0.7690, Val Loss: 1.2244, Val Accuracy: 0.6920 Epoch 5461/10000, Train Loss: 1.1451, Train Accuracy: 0.7734, Val Loss: 1.2245, Val Accuracy: 0.6875 Epoch 5462/10000, Train Loss: 1.1481, Train Accuracy: 0.7734, Val Loss: 1.2246, Val Accuracy: 0.6875 Epoch 5463/10000, Train Loss: 1.1424, Train Accuracy: 0.7801, Val Loss: 1.2246, Val Accuracy: 0.6875 Epoch 5464/10000, Train Loss: 1.1459, Train Accuracy: 0.7634, Val Loss: 1.2245, Val Accuracy: 0.6875 Epoch 5465/10000, Train Loss: 1.1426, Train Accuracy: 0.7790, Val Loss: 1.2244, Val Accuracy: 0.6875 Epoch 5466/10000, Train Loss: 1.1489, Train Accuracy: 0.7679, Val Loss: 1.2243, Val Accuracy: 0.6875 Epoch 5467/10000, Train Loss: 1.1416, Train Accuracy: 0.7690, Val Loss: 1.2244, Val Accuracy: 0.6875 Epoch 5468/10000, Train Loss: 1.1416, Train Accuracy: 0.7757, Val Loss: 1.2244, Val Accuracy: 0.6920 Epoch 5469/10000, Train Loss: 1.1416, Train Accuracy: 0.7712, Val Loss: 1.2244, Val Accuracy: 0.6830 Epoch 5470/10000, Train Loss: 1.1429, Train Accuracy: 0.7712, Val Loss: 1.2244, Val Accuracy: 0.6875 Epoch 5471/10000, Train Loss: 1.1409, Train Accuracy: 0.7734, Val Loss: 1.2244, Val Accuracy: 0.6875 Epoch 5472/10000, Train Loss: 1.1541, Train Accuracy: 0.7612, Val Loss: 1.2243, Val Accuracy: 0.6875 Epoch 5473/10000, Train Loss: 1.1434, Train Accuracy: 0.7679, Val Loss: 1.2242, Val Accuracy: 0.6830 Epoch 5474/10000, Train Loss: 1.1522, Train Accuracy: 0.7634, Val Loss: 1.2241, Val Accuracy: 0.6830 Epoch 5475/10000, Train Loss: 1.1429, Train Accuracy: 0.7712, Val Loss: 1.2238, Val Accuracy: 0.6875 Epoch 5476/10000, Train Loss: 1.1370, Train Accuracy: 0.7768, Val Loss: 1.2239, Val Accuracy: 0.6875 Epoch 5477/10000, Train Loss: 1.1475, Train Accuracy: 0.7746, Val Loss: 1.2237, Val Accuracy: 0.6875 Epoch 5478/10000, Train Loss: 1.1376, Train Accuracy: 0.7779, Val Loss: 1.2237, Val Accuracy: 0.6875 Epoch 5479/10000, Train Loss: 1.1455, Train Accuracy: 0.7645, Val Loss: 1.2235, Val Accuracy: 0.6875 Epoch 5480/10000, Train Loss: 1.1433, Train Accuracy: 0.7746, Val Loss: 1.2236, Val Accuracy: 0.6875 Epoch 5481/10000, Train Loss: 1.1464, Train Accuracy: 0.7645, Val Loss: 1.2235, Val Accuracy: 0.6920 Epoch 5482/10000, Train Loss: 1.1478, Train Accuracy: 0.7690, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5483/10000, Train Loss: 1.1391, Train Accuracy: 0.7768, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5484/10000, Train Loss: 1.1408, Train Accuracy: 0.7801, Val Loss: 1.2232, Val Accuracy: 0.6920 Epoch 5485/10000, Train Loss: 1.1385, Train Accuracy: 0.7868, Val Loss: 1.2230, Val Accuracy: 0.6920 Epoch 5486/10000, Train Loss: 1.1443, Train Accuracy: 0.7801, Val Loss: 1.2232, Val Accuracy: 0.6920 Epoch 5487/10000, Train Loss: 1.1441, Train Accuracy: 0.7812, Val Loss: 1.2232, Val Accuracy: 0.6920 Epoch 5488/10000, Train Loss: 1.1320, Train Accuracy: 0.7824, Val Loss: 1.2233, Val Accuracy: 0.6920 Epoch 5489/10000, Train Loss: 1.1362, Train Accuracy: 0.7801, Val Loss: 1.2233, Val Accuracy: 0.6920 Epoch 5490/10000, Train Loss: 1.1433, Train Accuracy: 0.7790, Val Loss: 1.2231, Val Accuracy: 0.6920 Epoch 5491/10000, Train Loss: 1.1463, Train Accuracy: 0.7701, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5492/10000, Train Loss: 1.1350, Train Accuracy: 0.7835, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5493/10000, Train Loss: 1.1404, Train Accuracy: 0.7701, Val Loss: 1.2229, Val Accuracy: 0.6875 Epoch 5494/10000, Train Loss: 1.1416, Train Accuracy: 0.7768, Val Loss: 1.2228, Val Accuracy: 0.6875 Epoch 5495/10000, Train Loss: 1.1361, Train Accuracy: 0.7790, Val Loss: 1.2229, Val Accuracy: 0.6875 Epoch 5496/10000, Train Loss: 1.1436, Train Accuracy: 0.7701, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5497/10000, Train Loss: 1.1473, Train Accuracy: 0.7679, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5498/10000, Train Loss: 1.1270, Train Accuracy: 0.7891, Val Loss: 1.2233, Val Accuracy: 0.6875 Epoch 5499/10000, Train Loss: 1.1364, Train Accuracy: 0.7790, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5500/10000, Train Loss: 1.1450, Train Accuracy: 0.7746, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5501/10000, Train Loss: 1.1578, Train Accuracy: 0.7522, Val Loss: 1.2230, Val Accuracy: 0.6875 Epoch 5502/10000, Train Loss: 1.1370, Train Accuracy: 0.7701, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5503/10000, Train Loss: 1.1419, Train Accuracy: 0.7768, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5504/10000, Train Loss: 1.1489, Train Accuracy: 0.7679, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5505/10000, Train Loss: 1.1477, Train Accuracy: 0.7634, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5506/10000, Train Loss: 1.1384, Train Accuracy: 0.7812, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5507/10000, Train Loss: 1.1421, Train Accuracy: 0.7734, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5508/10000, Train Loss: 1.1389, Train Accuracy: 0.7835, Val Loss: 1.2232, Val Accuracy: 0.6875 Epoch 5509/10000, Train Loss: 1.1413, Train Accuracy: 0.7757, Val Loss: 1.2235, Val Accuracy: 0.6875 Epoch 5510/10000, Train Loss: 1.1284, Train Accuracy: 0.7857, Val Loss: 1.2233, Val Accuracy: 0.6875 Epoch 5511/10000, Train Loss: 1.1350, Train Accuracy: 0.7768, Val Loss: 1.2236, Val Accuracy: 0.6875 Epoch 5512/10000, Train Loss: 1.1485, Train Accuracy: 0.7612, Val Loss: 1.2237, Val Accuracy: 0.6875 Epoch 5513/10000, Train Loss: 1.1404, Train Accuracy: 0.7835, Val Loss: 1.2237, Val Accuracy: 0.6875 Epoch 5514/10000, Train Loss: 1.1467, Train Accuracy: 0.7746, Val Loss: 1.2236, Val Accuracy: 0.6875 Epoch 5515/10000, Train Loss: 1.1488, Train Accuracy: 0.7645, Val Loss: 1.2235, Val Accuracy: 0.6875 Epoch 5516/10000, Train Loss: 1.1434, Train Accuracy: 0.7757, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5517/10000, Train Loss: 1.1446, Train Accuracy: 0.7656, Val Loss: 1.2233, Val Accuracy: 0.6875 Epoch 5518/10000, Train Loss: 1.1342, Train Accuracy: 0.7667, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5519/10000, Train Loss: 1.1375, Train Accuracy: 0.7857, Val Loss: 1.2231, Val Accuracy: 0.6875 Epoch 5520/10000, Train Loss: 1.1339, Train Accuracy: 0.7835, Val Loss: 1.2230, Val Accuracy: 0.6875 Epoch 5521/10000, Train Loss: 1.1339, Train Accuracy: 0.7868, Val Loss: 1.2229, Val Accuracy: 0.6875 Epoch 5522/10000, Train Loss: 1.1430, Train Accuracy: 0.7757, Val Loss: 1.2233, Val Accuracy: 0.6875 Epoch 5523/10000, Train Loss: 1.1340, Train Accuracy: 0.7846, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5524/10000, Train Loss: 1.1489, Train Accuracy: 0.7578, Val Loss: 1.2235, Val Accuracy: 0.6875 Epoch 5525/10000, Train Loss: 1.1399, Train Accuracy: 0.7746, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5526/10000, Train Loss: 1.1442, Train Accuracy: 0.7746, Val Loss: 1.2235, Val Accuracy: 0.6875 Epoch 5527/10000, Train Loss: 1.1333, Train Accuracy: 0.7801, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5528/10000, Train Loss: 1.1457, Train Accuracy: 0.7779, Val Loss: 1.2234, Val Accuracy: 0.6875 Epoch 5529/10000, Train Loss: 1.1402, Train Accuracy: 0.7679, Val Loss: 1.2233, Val Accuracy: 0.6875 Epoch 5530/10000, Train Loss: 1.1517, Train Accuracy: 0.7634, Val Loss: 1.2230, Val Accuracy: 0.6875 Epoch 5531/10000, Train Loss: 1.1467, Train Accuracy: 0.7723, Val Loss: 1.2228, Val Accuracy: 0.6875 Epoch 5532/10000, Train Loss: 1.1401, Train Accuracy: 0.7812, Val Loss: 1.2224, Val Accuracy: 0.6875 Epoch 5533/10000, Train Loss: 1.1412, Train Accuracy: 0.7779, Val Loss: 1.2222, Val Accuracy: 0.6875 Epoch 5534/10000, Train Loss: 1.1395, Train Accuracy: 0.7846, Val Loss: 1.2222, Val Accuracy: 0.6875 Epoch 5535/10000, Train Loss: 1.1342, Train Accuracy: 0.7824, Val Loss: 1.2222, Val Accuracy: 0.6875 Epoch 5536/10000, Train Loss: 1.1481, Train Accuracy: 0.7712, Val Loss: 1.2222, Val Accuracy: 0.6875 Epoch 5537/10000, Train Loss: 1.1369, Train Accuracy: 0.7868, Val Loss: 1.2221, Val Accuracy: 0.6875 Epoch 5538/10000, Train Loss: 1.1435, Train Accuracy: 0.7734, Val Loss: 1.2221, Val Accuracy: 0.6875 Epoch 5539/10000, Train Loss: 1.1431, Train Accuracy: 0.7701, Val Loss: 1.2219, Val Accuracy: 0.6875 Epoch 5540/10000, Train Loss: 1.1380, Train Accuracy: 0.7779, Val Loss: 1.2217, Val Accuracy: 0.6875 Epoch 5541/10000, Train Loss: 1.1507, Train Accuracy: 0.7600, Val Loss: 1.2218, Val Accuracy: 0.6875 Epoch 5542/10000, Train Loss: 1.1482, Train Accuracy: 0.7690, Val Loss: 1.2218, Val Accuracy: 0.6875 Epoch 5543/10000, Train Loss: 1.1466, Train Accuracy: 0.7690, Val Loss: 1.2215, Val Accuracy: 0.6875 Epoch 5544/10000, Train Loss: 1.1264, Train Accuracy: 0.7991, Val Loss: 1.2213, Val Accuracy: 0.6875 Epoch 5545/10000, Train Loss: 1.1496, Train Accuracy: 0.7612, Val Loss: 1.2208, Val Accuracy: 0.6875 Epoch 5546/10000, Train Loss: 1.1237, Train Accuracy: 0.7913, Val Loss: 1.2208, Val Accuracy: 0.6830 Epoch 5547/10000, Train Loss: 1.1373, Train Accuracy: 0.7812, Val Loss: 1.2207, Val Accuracy: 0.6830 Epoch 5548/10000, Train Loss: 1.1454, Train Accuracy: 0.7656, Val Loss: 1.2207, Val Accuracy: 0.6830 Epoch 5549/10000, Train Loss: 1.1465, Train Accuracy: 0.7712, Val Loss: 1.2208, Val Accuracy: 0.6830 Epoch 5550/10000, Train Loss: 1.1294, Train Accuracy: 0.7812, Val Loss: 1.2208, Val Accuracy: 0.6875 Epoch 5551/10000, Train Loss: 1.1358, Train Accuracy: 0.7801, Val Loss: 1.2207, Val Accuracy: 0.6875 Epoch 5552/10000, Train Loss: 1.1346, Train Accuracy: 0.7879, Val Loss: 1.2207, Val Accuracy: 0.6875 Epoch 5553/10000, Train Loss: 1.1428, Train Accuracy: 0.7790, Val Loss: 1.2206, Val Accuracy: 0.6875 Epoch 5554/10000, Train Loss: 1.1516, Train Accuracy: 0.7623, Val Loss: 1.2206, Val Accuracy: 0.6875 Epoch 5555/10000, Train Loss: 1.1402, Train Accuracy: 0.7746, Val Loss: 1.2207, Val Accuracy: 0.6875 Epoch 5556/10000, Train Loss: 1.1374, Train Accuracy: 0.7824, Val Loss: 1.2208, Val Accuracy: 0.6830 Epoch 5557/10000, Train Loss: 1.1325, Train Accuracy: 0.7801, Val Loss: 1.2206, Val Accuracy: 0.6875 Epoch 5558/10000, Train Loss: 1.1300, Train Accuracy: 0.7846, Val Loss: 1.2204, Val Accuracy: 0.6920 Epoch 5559/10000, Train Loss: 1.1472, Train Accuracy: 0.7623, Val Loss: 1.2206, Val Accuracy: 0.6875 Epoch 5560/10000, Train Loss: 1.1418, Train Accuracy: 0.7801, Val Loss: 1.2205, Val Accuracy: 0.6875 Epoch 5561/10000, Train Loss: 1.1371, Train Accuracy: 0.7779, Val Loss: 1.2203, Val Accuracy: 0.6875 Epoch 5562/10000, Train Loss: 1.1344, Train Accuracy: 0.7768, Val Loss: 1.2205, Val Accuracy: 0.6875 Epoch 5563/10000, Train Loss: 1.1269, Train Accuracy: 0.7902, Val Loss: 1.2205, Val Accuracy: 0.6920 Epoch 5564/10000, Train Loss: 1.1398, Train Accuracy: 0.7790, Val Loss: 1.2204, Val Accuracy: 0.6920 Epoch 5565/10000, Train Loss: 1.1392, Train Accuracy: 0.7768, Val Loss: 1.2205, Val Accuracy: 0.6920 Epoch 5566/10000, Train Loss: 1.1455, Train Accuracy: 0.7746, Val Loss: 1.2206, Val Accuracy: 0.6964 Epoch 5567/10000, Train Loss: 1.1372, Train Accuracy: 0.7712, Val Loss: 1.2206, Val Accuracy: 0.6964 Epoch 5568/10000, Train Loss: 1.1348, Train Accuracy: 0.7790, Val Loss: 1.2203, Val Accuracy: 0.6920 Epoch 5569/10000, Train Loss: 1.1382, Train Accuracy: 0.7868, Val Loss: 1.2201, Val Accuracy: 0.6920 Epoch 5570/10000, Train Loss: 1.1155, Train Accuracy: 0.8036, Val Loss: 1.2200, Val Accuracy: 0.6920 Epoch 5571/10000, Train Loss: 1.1357, Train Accuracy: 0.7846, Val Loss: 1.2199, Val Accuracy: 0.6920 Epoch 5572/10000, Train Loss: 1.1429, Train Accuracy: 0.7746, Val Loss: 1.2198, Val Accuracy: 0.6920 Epoch 5573/10000, Train Loss: 1.1354, Train Accuracy: 0.7801, Val Loss: 1.2197, Val Accuracy: 0.6920 Epoch 5574/10000, Train Loss: 1.1333, Train Accuracy: 0.7924, Val Loss: 1.2197, Val Accuracy: 0.6920 Epoch 5575/10000, Train Loss: 1.1453, Train Accuracy: 0.7712, Val Loss: 1.2196, Val Accuracy: 0.6920 Epoch 5576/10000, Train Loss: 1.1322, Train Accuracy: 0.7913, Val Loss: 1.2194, Val Accuracy: 0.6920 Epoch 5577/10000, Train Loss: 1.1465, Train Accuracy: 0.7679, Val Loss: 1.2196, Val Accuracy: 0.6920 Epoch 5578/10000, Train Loss: 1.1330, Train Accuracy: 0.7924, Val Loss: 1.2199, Val Accuracy: 0.6920 Epoch 5579/10000, Train Loss: 1.1381, Train Accuracy: 0.7723, Val Loss: 1.2197, Val Accuracy: 0.6920 Epoch 5580/10000, Train Loss: 1.1359, Train Accuracy: 0.7734, Val Loss: 1.2196, Val Accuracy: 0.6920 Epoch 5581/10000, Train Loss: 1.1292, Train Accuracy: 0.7980, Val Loss: 1.2194, Val Accuracy: 0.6964 Epoch 5582/10000, Train Loss: 1.1308, Train Accuracy: 0.7946, Val Loss: 1.2193, Val Accuracy: 0.6920 Epoch 5583/10000, Train Loss: 1.1385, Train Accuracy: 0.7768, Val Loss: 1.2194, Val Accuracy: 0.6920 Epoch 5584/10000, Train Loss: 1.1412, Train Accuracy: 0.7679, Val Loss: 1.2195, Val Accuracy: 0.6920 Epoch 5585/10000, Train Loss: 1.1294, Train Accuracy: 0.7902, Val Loss: 1.2192, Val Accuracy: 0.6920 Epoch 5586/10000, Train Loss: 1.1323, Train Accuracy: 0.7824, Val Loss: 1.2191, Val Accuracy: 0.6964 Epoch 5587/10000, Train Loss: 1.1366, Train Accuracy: 0.7812, Val Loss: 1.2191, Val Accuracy: 0.6964 Epoch 5588/10000, Train Loss: 1.1354, Train Accuracy: 0.7779, Val Loss: 1.2194, Val Accuracy: 0.6964 Epoch 5589/10000, Train Loss: 1.1355, Train Accuracy: 0.7757, Val Loss: 1.2195, Val Accuracy: 0.6920 Epoch 5590/10000, Train Loss: 1.1419, Train Accuracy: 0.7790, Val Loss: 1.2196, Val Accuracy: 0.6920 Epoch 5591/10000, Train Loss: 1.1399, Train Accuracy: 0.7779, Val Loss: 1.2198, Val Accuracy: 0.6920 Epoch 5592/10000, Train Loss: 1.1498, Train Accuracy: 0.7578, Val Loss: 1.2196, Val Accuracy: 0.6920 Epoch 5593/10000, Train Loss: 1.1425, Train Accuracy: 0.7734, Val Loss: 1.2196, Val Accuracy: 0.6964 Epoch 5594/10000, Train Loss: 1.1338, Train Accuracy: 0.7812, Val Loss: 1.2194, Val Accuracy: 0.6964 Epoch 5595/10000, Train Loss: 1.1330, Train Accuracy: 0.7868, Val Loss: 1.2195, Val Accuracy: 0.6964 Epoch 5596/10000, Train Loss: 1.1405, Train Accuracy: 0.7779, Val Loss: 1.2194, Val Accuracy: 0.6920 Epoch 5597/10000, Train Loss: 1.1306, Train Accuracy: 0.7891, Val Loss: 1.2192, Val Accuracy: 0.6920 Epoch 5598/10000, Train Loss: 1.1365, Train Accuracy: 0.7824, Val Loss: 1.2194, Val Accuracy: 0.6920 Epoch 5599/10000, Train Loss: 1.1361, Train Accuracy: 0.7757, Val Loss: 1.2191, Val Accuracy: 0.6920 Epoch 5600/10000, Train Loss: 1.1432, Train Accuracy: 0.7679, Val Loss: 1.2189, Val Accuracy: 0.6964 Epoch 5601/10000, Train Loss: 1.1340, Train Accuracy: 0.7801, Val Loss: 1.2189, Val Accuracy: 0.6964 Epoch 5602/10000, Train Loss: 1.1445, Train Accuracy: 0.7723, Val Loss: 1.2189, Val Accuracy: 0.6920 Epoch 5603/10000, Train Loss: 1.1312, Train Accuracy: 0.7891, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5604/10000, Train Loss: 1.1308, Train Accuracy: 0.7980, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5605/10000, Train Loss: 1.1303, Train Accuracy: 0.7891, Val Loss: 1.2185, Val Accuracy: 0.6964 Epoch 5606/10000, Train Loss: 1.1451, Train Accuracy: 0.7690, Val Loss: 1.2186, Val Accuracy: 0.6964 Epoch 5607/10000, Train Loss: 1.1417, Train Accuracy: 0.7757, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5608/10000, Train Loss: 1.1339, Train Accuracy: 0.7801, Val Loss: 1.2188, Val Accuracy: 0.6964 Epoch 5609/10000, Train Loss: 1.1317, Train Accuracy: 0.7935, Val Loss: 1.2188, Val Accuracy: 0.6920 Epoch 5610/10000, Train Loss: 1.1373, Train Accuracy: 0.7734, Val Loss: 1.2189, Val Accuracy: 0.6964 Epoch 5611/10000, Train Loss: 1.1300, Train Accuracy: 0.7913, Val Loss: 1.2188, Val Accuracy: 0.6964 Epoch 5612/10000, Train Loss: 1.1253, Train Accuracy: 0.7879, Val Loss: 1.2187, Val Accuracy: 0.6920 Epoch 5613/10000, Train Loss: 1.1462, Train Accuracy: 0.7757, Val Loss: 1.2190, Val Accuracy: 0.6964 Epoch 5614/10000, Train Loss: 1.1284, Train Accuracy: 0.7924, Val Loss: 1.2191, Val Accuracy: 0.6964 Epoch 5615/10000, Train Loss: 1.1399, Train Accuracy: 0.7757, Val Loss: 1.2189, Val Accuracy: 0.6964 Epoch 5616/10000, Train Loss: 1.1248, Train Accuracy: 0.7924, Val Loss: 1.2189, Val Accuracy: 0.6964 Epoch 5617/10000, Train Loss: 1.1340, Train Accuracy: 0.7779, Val Loss: 1.2188, Val Accuracy: 0.6964 Epoch 5618/10000, Train Loss: 1.1327, Train Accuracy: 0.7801, Val Loss: 1.2187, Val Accuracy: 0.6920 Epoch 5619/10000, Train Loss: 1.1376, Train Accuracy: 0.7812, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5620/10000, Train Loss: 1.1464, Train Accuracy: 0.7623, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5621/10000, Train Loss: 1.1471, Train Accuracy: 0.7567, Val Loss: 1.2186, Val Accuracy: 0.7009 Epoch 5622/10000, Train Loss: 1.1251, Train Accuracy: 0.7980, Val Loss: 1.2184, Val Accuracy: 0.7009 Epoch 5623/10000, Train Loss: 1.1422, Train Accuracy: 0.7779, Val Loss: 1.2187, Val Accuracy: 0.7009 Epoch 5624/10000, Train Loss: 1.1381, Train Accuracy: 0.7768, Val Loss: 1.2188, Val Accuracy: 0.7009 Epoch 5625/10000, Train Loss: 1.1343, Train Accuracy: 0.7835, Val Loss: 1.2188, Val Accuracy: 0.6964 Epoch 5626/10000, Train Loss: 1.1330, Train Accuracy: 0.7846, Val Loss: 1.2184, Val Accuracy: 0.6964 Epoch 5627/10000, Train Loss: 1.1331, Train Accuracy: 0.7757, Val Loss: 1.2184, Val Accuracy: 0.7009 Epoch 5628/10000, Train Loss: 1.1472, Train Accuracy: 0.7645, Val Loss: 1.2186, Val Accuracy: 0.6964 Epoch 5629/10000, Train Loss: 1.1398, Train Accuracy: 0.7801, Val Loss: 1.2186, Val Accuracy: 0.6964 Epoch 5630/10000, Train Loss: 1.1325, Train Accuracy: 0.7958, Val Loss: 1.2186, Val Accuracy: 0.6964 Epoch 5631/10000, Train Loss: 1.1355, Train Accuracy: 0.7790, Val Loss: 1.2185, Val Accuracy: 0.6964 Epoch 5632/10000, Train Loss: 1.1367, Train Accuracy: 0.7835, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5633/10000, Train Loss: 1.1368, Train Accuracy: 0.7723, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5634/10000, Train Loss: 1.1410, Train Accuracy: 0.7746, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5635/10000, Train Loss: 1.1298, Train Accuracy: 0.7868, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5636/10000, Train Loss: 1.1312, Train Accuracy: 0.7879, Val Loss: 1.2185, Val Accuracy: 0.6920 Epoch 5637/10000, Train Loss: 1.1337, Train Accuracy: 0.7812, Val Loss: 1.2184, Val Accuracy: 0.7009 Epoch 5638/10000, Train Loss: 1.1319, Train Accuracy: 0.7801, Val Loss: 1.2185, Val Accuracy: 0.7009 Epoch 5639/10000, Train Loss: 1.1349, Train Accuracy: 0.7846, Val Loss: 1.2184, Val Accuracy: 0.7009 Epoch 5640/10000, Train Loss: 1.1447, Train Accuracy: 0.7612, Val Loss: 1.2184, Val Accuracy: 0.7009 Epoch 5641/10000, Train Loss: 1.1305, Train Accuracy: 0.7891, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5642/10000, Train Loss: 1.1452, Train Accuracy: 0.7656, Val Loss: 1.2188, Val Accuracy: 0.7009 Epoch 5643/10000, Train Loss: 1.1416, Train Accuracy: 0.7746, Val Loss: 1.2188, Val Accuracy: 0.7009 Epoch 5644/10000, Train Loss: 1.1332, Train Accuracy: 0.7891, Val Loss: 1.2185, Val Accuracy: 0.6964 Epoch 5645/10000, Train Loss: 1.1313, Train Accuracy: 0.7991, Val Loss: 1.2184, Val Accuracy: 0.6964 Epoch 5646/10000, Train Loss: 1.1324, Train Accuracy: 0.7757, Val Loss: 1.2187, Val Accuracy: 0.6920 Epoch 5647/10000, Train Loss: 1.1420, Train Accuracy: 0.7645, Val Loss: 1.2186, Val Accuracy: 0.6920 Epoch 5648/10000, Train Loss: 1.1360, Train Accuracy: 0.7790, Val Loss: 1.2186, Val Accuracy: 0.6920 Epoch 5649/10000, Train Loss: 1.1314, Train Accuracy: 0.7835, Val Loss: 1.2187, Val Accuracy: 0.6964 Epoch 5650/10000, Train Loss: 1.1343, Train Accuracy: 0.7835, Val Loss: 1.2183, Val Accuracy: 0.6964 Epoch 5651/10000, Train Loss: 1.1224, Train Accuracy: 0.7935, Val Loss: 1.2181, Val Accuracy: 0.6964 Epoch 5652/10000, Train Loss: 1.1382, Train Accuracy: 0.7679, Val Loss: 1.2181, Val Accuracy: 0.6964 Epoch 5653/10000, Train Loss: 1.1253, Train Accuracy: 0.8002, Val Loss: 1.2181, Val Accuracy: 0.6920 Epoch 5654/10000, Train Loss: 1.1325, Train Accuracy: 0.7935, Val Loss: 1.2182, Val Accuracy: 0.6920 Epoch 5655/10000, Train Loss: 1.1319, Train Accuracy: 0.7835, Val Loss: 1.2180, Val Accuracy: 0.6920 Epoch 5656/10000, Train Loss: 1.1406, Train Accuracy: 0.7656, Val Loss: 1.2180, Val Accuracy: 0.6875 Epoch 5657/10000, Train Loss: 1.1413, Train Accuracy: 0.7712, Val Loss: 1.2180, Val Accuracy: 0.6920 Epoch 5658/10000, Train Loss: 1.1370, Train Accuracy: 0.7757, Val Loss: 1.2181, Val Accuracy: 0.7009 Epoch 5659/10000, Train Loss: 1.1390, Train Accuracy: 0.7790, Val Loss: 1.2182, Val Accuracy: 0.6920 Epoch 5660/10000, Train Loss: 1.1226, Train Accuracy: 0.7935, Val Loss: 1.2179, Val Accuracy: 0.6920 Epoch 5661/10000, Train Loss: 1.1272, Train Accuracy: 0.7980, Val Loss: 1.2178, Val Accuracy: 0.6875 Epoch 5662/10000, Train Loss: 1.1454, Train Accuracy: 0.7679, Val Loss: 1.2176, Val Accuracy: 0.6920 Epoch 5663/10000, Train Loss: 1.1331, Train Accuracy: 0.7779, Val Loss: 1.2178, Val Accuracy: 0.6920 Epoch 5664/10000, Train Loss: 1.1375, Train Accuracy: 0.7812, Val Loss: 1.2177, Val Accuracy: 0.6920 Epoch 5665/10000, Train Loss: 1.1389, Train Accuracy: 0.7835, Val Loss: 1.2177, Val Accuracy: 0.6920 Epoch 5666/10000, Train Loss: 1.1224, Train Accuracy: 0.8025, Val Loss: 1.2176, Val Accuracy: 0.6875 Epoch 5667/10000, Train Loss: 1.1333, Train Accuracy: 0.7779, Val Loss: 1.2174, Val Accuracy: 0.6920 Epoch 5668/10000, Train Loss: 1.1446, Train Accuracy: 0.7667, Val Loss: 1.2173, Val Accuracy: 0.6875 Epoch 5669/10000, Train Loss: 1.1256, Train Accuracy: 0.7935, Val Loss: 1.2172, Val Accuracy: 0.6875 Epoch 5670/10000, Train Loss: 1.1316, Train Accuracy: 0.7958, Val Loss: 1.2173, Val Accuracy: 0.6920 Epoch 5671/10000, Train Loss: 1.1191, Train Accuracy: 0.7991, Val Loss: 1.2171, Val Accuracy: 0.6964 Epoch 5672/10000, Train Loss: 1.1432, Train Accuracy: 0.7679, Val Loss: 1.2171, Val Accuracy: 0.6875 Epoch 5673/10000, Train Loss: 1.1292, Train Accuracy: 0.7891, Val Loss: 1.2173, Val Accuracy: 0.6875 Epoch 5674/10000, Train Loss: 1.1297, Train Accuracy: 0.7924, Val Loss: 1.2173, Val Accuracy: 0.6964 Epoch 5675/10000, Train Loss: 1.1397, Train Accuracy: 0.7723, Val Loss: 1.2172, Val Accuracy: 0.6964 Epoch 5676/10000, Train Loss: 1.1260, Train Accuracy: 0.7846, Val Loss: 1.2174, Val Accuracy: 0.6964 Epoch 5677/10000, Train Loss: 1.1365, Train Accuracy: 0.7790, Val Loss: 1.2173, Val Accuracy: 0.6964 Epoch 5678/10000, Train Loss: 1.1348, Train Accuracy: 0.7824, Val Loss: 1.2172, Val Accuracy: 0.6964 Epoch 5679/10000, Train Loss: 1.1350, Train Accuracy: 0.7835, Val Loss: 1.2172, Val Accuracy: 0.6964 Epoch 5680/10000, Train Loss: 1.1434, Train Accuracy: 0.7712, Val Loss: 1.2172, Val Accuracy: 0.6964 Epoch 5681/10000, Train Loss: 1.1357, Train Accuracy: 0.7779, Val Loss: 1.2171, Val Accuracy: 0.6875 Epoch 5682/10000, Train Loss: 1.1328, Train Accuracy: 0.7902, Val Loss: 1.2172, Val Accuracy: 0.6875 Epoch 5683/10000, Train Loss: 1.1273, Train Accuracy: 0.7924, Val Loss: 1.2169, Val Accuracy: 0.6920 Epoch 5684/10000, Train Loss: 1.1287, Train Accuracy: 0.7891, Val Loss: 1.2169, Val Accuracy: 0.6920 Epoch 5685/10000, Train Loss: 1.1292, Train Accuracy: 0.7868, Val Loss: 1.2167, Val Accuracy: 0.6920 Epoch 5686/10000, Train Loss: 1.1326, Train Accuracy: 0.7913, Val Loss: 1.2169, Val Accuracy: 0.6875 Epoch 5687/10000, Train Loss: 1.1493, Train Accuracy: 0.7578, Val Loss: 1.2169, Val Accuracy: 0.6920 Epoch 5688/10000, Train Loss: 1.1325, Train Accuracy: 0.7812, Val Loss: 1.2171, Val Accuracy: 0.6920 Epoch 5689/10000, Train Loss: 1.1330, Train Accuracy: 0.7879, Val Loss: 1.2171, Val Accuracy: 0.6920 Epoch 5690/10000, Train Loss: 1.1400, Train Accuracy: 0.7690, Val Loss: 1.2169, Val Accuracy: 0.6920 Epoch 5691/10000, Train Loss: 1.1243, Train Accuracy: 0.7980, Val Loss: 1.2168, Val Accuracy: 0.6920 Epoch 5692/10000, Train Loss: 1.1257, Train Accuracy: 0.7946, Val Loss: 1.2168, Val Accuracy: 0.6920 Epoch 5693/10000, Train Loss: 1.1383, Train Accuracy: 0.7734, Val Loss: 1.2167, Val Accuracy: 0.6920 Epoch 5694/10000, Train Loss: 1.1345, Train Accuracy: 0.7734, Val Loss: 1.2165, Val Accuracy: 0.6920 Epoch 5695/10000, Train Loss: 1.1445, Train Accuracy: 0.7712, Val Loss: 1.2163, Val Accuracy: 0.6920 Epoch 5696/10000, Train Loss: 1.1189, Train Accuracy: 0.7980, Val Loss: 1.2162, Val Accuracy: 0.6920 Epoch 5697/10000, Train Loss: 1.1321, Train Accuracy: 0.7868, Val Loss: 1.2165, Val Accuracy: 0.6920 Epoch 5698/10000, Train Loss: 1.1225, Train Accuracy: 0.7980, Val Loss: 1.2162, Val Accuracy: 0.6920 Epoch 5699/10000, Train Loss: 1.1304, Train Accuracy: 0.7902, Val Loss: 1.2161, Val Accuracy: 0.6964 Epoch 5700/10000, Train Loss: 1.1297, Train Accuracy: 0.7902, Val Loss: 1.2160, Val Accuracy: 0.6964 Epoch 5701/10000, Train Loss: 1.1364, Train Accuracy: 0.7824, Val Loss: 1.2159, Val Accuracy: 0.6920 Epoch 5702/10000, Train Loss: 1.1307, Train Accuracy: 0.7958, Val Loss: 1.2156, Val Accuracy: 0.6920 Epoch 5703/10000, Train Loss: 1.1192, Train Accuracy: 0.8069, Val Loss: 1.2157, Val Accuracy: 0.6920 Epoch 5704/10000, Train Loss: 1.1291, Train Accuracy: 0.7868, Val Loss: 1.2156, Val Accuracy: 0.6920 Epoch 5705/10000, Train Loss: 1.1339, Train Accuracy: 0.7790, Val Loss: 1.2157, Val Accuracy: 0.6920 Epoch 5706/10000, Train Loss: 1.1411, Train Accuracy: 0.7656, Val Loss: 1.2155, Val Accuracy: 0.6920 Epoch 5707/10000, Train Loss: 1.1333, Train Accuracy: 0.7723, Val Loss: 1.2153, Val Accuracy: 0.6920 Epoch 5708/10000, Train Loss: 1.1380, Train Accuracy: 0.7779, Val Loss: 1.2156, Val Accuracy: 0.6920 Epoch 5709/10000, Train Loss: 1.1305, Train Accuracy: 0.7846, Val Loss: 1.2155, Val Accuracy: 0.6920 Epoch 5710/10000, Train Loss: 1.1230, Train Accuracy: 0.7980, Val Loss: 1.2155, Val Accuracy: 0.6920 Epoch 5711/10000, Train Loss: 1.1250, Train Accuracy: 0.7969, Val Loss: 1.2153, Val Accuracy: 0.6920 Epoch 5712/10000, Train Loss: 1.1395, Train Accuracy: 0.7723, Val Loss: 1.2155, Val Accuracy: 0.6920 Epoch 5713/10000, Train Loss: 1.1349, Train Accuracy: 0.7734, Val Loss: 1.2157, Val Accuracy: 0.6920 Epoch 5714/10000, Train Loss: 1.1253, Train Accuracy: 0.7879, Val Loss: 1.2154, Val Accuracy: 0.6920 Epoch 5715/10000, Train Loss: 1.1412, Train Accuracy: 0.7746, Val Loss: 1.2155, Val Accuracy: 0.6920 Epoch 5716/10000, Train Loss: 1.1261, Train Accuracy: 0.7935, Val Loss: 1.2151, Val Accuracy: 0.6920 Epoch 5717/10000, Train Loss: 1.1325, Train Accuracy: 0.7868, Val Loss: 1.2153, Val Accuracy: 0.6964 Epoch 5718/10000, Train Loss: 1.1304, Train Accuracy: 0.7801, Val Loss: 1.2154, Val Accuracy: 0.6920 Epoch 5719/10000, Train Loss: 1.1353, Train Accuracy: 0.7857, Val Loss: 1.2152, Val Accuracy: 0.6920 Epoch 5720/10000, Train Loss: 1.1259, Train Accuracy: 0.7969, Val Loss: 1.2150, Val Accuracy: 0.6964 Epoch 5721/10000, Train Loss: 1.1242, Train Accuracy: 0.7902, Val Loss: 1.2150, Val Accuracy: 0.6964 Epoch 5722/10000, Train Loss: 1.1301, Train Accuracy: 0.7790, Val Loss: 1.2150, Val Accuracy: 0.7009 Epoch 5723/10000, Train Loss: 1.1360, Train Accuracy: 0.7835, Val Loss: 1.2148, Val Accuracy: 0.7009 Epoch 5724/10000, Train Loss: 1.1299, Train Accuracy: 0.7857, Val Loss: 1.2148, Val Accuracy: 0.7009 Epoch 5725/10000, Train Loss: 1.1263, Train Accuracy: 0.7879, Val Loss: 1.2148, Val Accuracy: 0.7009 Epoch 5726/10000, Train Loss: 1.1436, Train Accuracy: 0.7712, Val Loss: 1.2148, Val Accuracy: 0.7009 Epoch 5727/10000, Train Loss: 1.1280, Train Accuracy: 0.7902, Val Loss: 1.2148, Val Accuracy: 0.7009 Epoch 5728/10000, Train Loss: 1.1344, Train Accuracy: 0.7790, Val Loss: 1.2148, Val Accuracy: 0.6964 Epoch 5729/10000, Train Loss: 1.1248, Train Accuracy: 0.7902, Val Loss: 1.2145, Val Accuracy: 0.7009 Epoch 5730/10000, Train Loss: 1.1232, Train Accuracy: 0.7935, Val Loss: 1.2142, Val Accuracy: 0.7009 Epoch 5731/10000, Train Loss: 1.1226, Train Accuracy: 0.7991, Val Loss: 1.2143, Val Accuracy: 0.7009 Epoch 5732/10000, Train Loss: 1.1227, Train Accuracy: 0.7969, Val Loss: 1.2143, Val Accuracy: 0.6964 Epoch 5733/10000, Train Loss: 1.1333, Train Accuracy: 0.7734, Val Loss: 1.2140, Val Accuracy: 0.7009 Epoch 5734/10000, Train Loss: 1.1319, Train Accuracy: 0.7868, Val Loss: 1.2144, Val Accuracy: 0.7009 Epoch 5735/10000, Train Loss: 1.1396, Train Accuracy: 0.7712, Val Loss: 1.2143, Val Accuracy: 0.7009 Epoch 5736/10000, Train Loss: 1.1352, Train Accuracy: 0.7801, Val Loss: 1.2144, Val Accuracy: 0.6964 Epoch 5737/10000, Train Loss: 1.1345, Train Accuracy: 0.7835, Val Loss: 1.2146, Val Accuracy: 0.6964 Epoch 5738/10000, Train Loss: 1.1244, Train Accuracy: 0.7891, Val Loss: 1.2147, Val Accuracy: 0.6964 Epoch 5739/10000, Train Loss: 1.1429, Train Accuracy: 0.7712, Val Loss: 1.2149, Val Accuracy: 0.6964 Epoch 5740/10000, Train Loss: 1.1338, Train Accuracy: 0.7824, Val Loss: 1.2148, Val Accuracy: 0.6964 Epoch 5741/10000, Train Loss: 1.1234, Train Accuracy: 0.7935, Val Loss: 1.2148, Val Accuracy: 0.6964 Epoch 5742/10000, Train Loss: 1.1230, Train Accuracy: 0.8002, Val Loss: 1.2147, Val Accuracy: 0.6964 Epoch 5743/10000, Train Loss: 1.1261, Train Accuracy: 0.7891, Val Loss: 1.2146, Val Accuracy: 0.6964 Epoch 5744/10000, Train Loss: 1.1367, Train Accuracy: 0.7779, Val Loss: 1.2145, Val Accuracy: 0.6964 Epoch 5745/10000, Train Loss: 1.1344, Train Accuracy: 0.7757, Val Loss: 1.2143, Val Accuracy: 0.6964 Epoch 5746/10000, Train Loss: 1.1185, Train Accuracy: 0.8013, Val Loss: 1.2141, Val Accuracy: 0.6964 Epoch 5747/10000, Train Loss: 1.1427, Train Accuracy: 0.7656, Val Loss: 1.2142, Val Accuracy: 0.6964 Epoch 5748/10000, Train Loss: 1.1290, Train Accuracy: 0.7879, Val Loss: 1.2143, Val Accuracy: 0.6964 Epoch 5749/10000, Train Loss: 1.1392, Train Accuracy: 0.7757, Val Loss: 1.2142, Val Accuracy: 0.6964 Epoch 5750/10000, Train Loss: 1.1310, Train Accuracy: 0.7824, Val Loss: 1.2140, Val Accuracy: 0.6964 Epoch 5751/10000, Train Loss: 1.1345, Train Accuracy: 0.7768, Val Loss: 1.2137, Val Accuracy: 0.6964 Epoch 5752/10000, Train Loss: 1.1308, Train Accuracy: 0.7868, Val Loss: 1.2136, Val Accuracy: 0.6964 Epoch 5753/10000, Train Loss: 1.1209, Train Accuracy: 0.7913, Val Loss: 1.2132, Val Accuracy: 0.6964 Epoch 5754/10000, Train Loss: 1.1297, Train Accuracy: 0.7824, Val Loss: 1.2133, Val Accuracy: 0.7009 Epoch 5755/10000, Train Loss: 1.1184, Train Accuracy: 0.7969, Val Loss: 1.2131, Val Accuracy: 0.7009 Epoch 5756/10000, Train Loss: 1.1362, Train Accuracy: 0.7734, Val Loss: 1.2132, Val Accuracy: 0.6964 Epoch 5757/10000, Train Loss: 1.1346, Train Accuracy: 0.7790, Val Loss: 1.2129, Val Accuracy: 0.7009 Epoch 5758/10000, Train Loss: 1.1279, Train Accuracy: 0.7857, Val Loss: 1.2129, Val Accuracy: 0.7009 Epoch 5759/10000, Train Loss: 1.1303, Train Accuracy: 0.7824, Val Loss: 1.2130, Val Accuracy: 0.7009 Epoch 5760/10000, Train Loss: 1.1265, Train Accuracy: 0.7913, Val Loss: 1.2130, Val Accuracy: 0.7009 Epoch 5761/10000, Train Loss: 1.1211, Train Accuracy: 0.7935, Val Loss: 1.2127, Val Accuracy: 0.7009 Epoch 5762/10000, Train Loss: 1.1314, Train Accuracy: 0.7935, Val Loss: 1.2127, Val Accuracy: 0.7009 Epoch 5763/10000, Train Loss: 1.1204, Train Accuracy: 0.7935, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5764/10000, Train Loss: 1.1417, Train Accuracy: 0.7667, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5765/10000, Train Loss: 1.1207, Train Accuracy: 0.7913, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5766/10000, Train Loss: 1.1379, Train Accuracy: 0.7768, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5767/10000, Train Loss: 1.1337, Train Accuracy: 0.7824, Val Loss: 1.2123, Val Accuracy: 0.7009 Epoch 5768/10000, Train Loss: 1.1314, Train Accuracy: 0.7812, Val Loss: 1.2125, Val Accuracy: 0.7009 Epoch 5769/10000, Train Loss: 1.1172, Train Accuracy: 0.8025, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5770/10000, Train Loss: 1.1337, Train Accuracy: 0.7801, Val Loss: 1.2125, Val Accuracy: 0.7009 Epoch 5771/10000, Train Loss: 1.1244, Train Accuracy: 0.7935, Val Loss: 1.2123, Val Accuracy: 0.7009 Epoch 5772/10000, Train Loss: 1.1307, Train Accuracy: 0.7757, Val Loss: 1.2121, Val Accuracy: 0.7009 Epoch 5773/10000, Train Loss: 1.1300, Train Accuracy: 0.7812, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5774/10000, Train Loss: 1.1284, Train Accuracy: 0.7902, Val Loss: 1.2122, Val Accuracy: 0.7009 Epoch 5775/10000, Train Loss: 1.1221, Train Accuracy: 0.7946, Val Loss: 1.2122, Val Accuracy: 0.7009 Epoch 5776/10000, Train Loss: 1.1222, Train Accuracy: 0.7913, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5777/10000, Train Loss: 1.1413, Train Accuracy: 0.7656, Val Loss: 1.2124, Val Accuracy: 0.7009 Epoch 5778/10000, Train Loss: 1.1313, Train Accuracy: 0.7868, Val Loss: 1.2124, Val Accuracy: 0.7054 Epoch 5779/10000, Train Loss: 1.1266, Train Accuracy: 0.7980, Val Loss: 1.2126, Val Accuracy: 0.7009 Epoch 5780/10000, Train Loss: 1.1245, Train Accuracy: 0.7924, Val Loss: 1.2125, Val Accuracy: 0.7009 Epoch 5781/10000, Train Loss: 1.1364, Train Accuracy: 0.7790, Val Loss: 1.2122, Val Accuracy: 0.7009 Epoch 5782/10000, Train Loss: 1.1230, Train Accuracy: 0.7913, Val Loss: 1.2122, Val Accuracy: 0.7009 Epoch 5783/10000, Train Loss: 1.1190, Train Accuracy: 0.8013, Val Loss: 1.2122, Val Accuracy: 0.7009 Epoch 5784/10000, Train Loss: 1.1217, Train Accuracy: 0.7935, Val Loss: 1.2121, Val Accuracy: 0.7054 Epoch 5785/10000, Train Loss: 1.1262, Train Accuracy: 0.7868, Val Loss: 1.2120, Val Accuracy: 0.7054 Epoch 5786/10000, Train Loss: 1.1161, Train Accuracy: 0.8036, Val Loss: 1.2119, Val Accuracy: 0.7009 Epoch 5787/10000, Train Loss: 1.1306, Train Accuracy: 0.7790, Val Loss: 1.2118, Val Accuracy: 0.7009 Epoch 5788/10000, Train Loss: 1.1210, Train Accuracy: 0.8013, Val Loss: 1.2117, Val Accuracy: 0.7054 Epoch 5789/10000, Train Loss: 1.1354, Train Accuracy: 0.7746, Val Loss: 1.2115, Val Accuracy: 0.7054 Epoch 5790/10000, Train Loss: 1.1290, Train Accuracy: 0.7891, Val Loss: 1.2115, Val Accuracy: 0.7054 Epoch 5791/10000, Train Loss: 1.1428, Train Accuracy: 0.7723, Val Loss: 1.2117, Val Accuracy: 0.7054 Epoch 5792/10000, Train Loss: 1.1196, Train Accuracy: 0.7969, Val Loss: 1.2118, Val Accuracy: 0.7054 Epoch 5793/10000, Train Loss: 1.1275, Train Accuracy: 0.7879, Val Loss: 1.2118, Val Accuracy: 0.7054 Epoch 5794/10000, Train Loss: 1.1303, Train Accuracy: 0.7790, Val Loss: 1.2117, Val Accuracy: 0.7054 Epoch 5795/10000, Train Loss: 1.1288, Train Accuracy: 0.7935, Val Loss: 1.2118, Val Accuracy: 0.7009 Epoch 5796/10000, Train Loss: 1.1289, Train Accuracy: 0.7790, Val Loss: 1.2117, Val Accuracy: 0.7054 Epoch 5797/10000, Train Loss: 1.1340, Train Accuracy: 0.7801, Val Loss: 1.2119, Val Accuracy: 0.7054 Epoch 5798/10000, Train Loss: 1.1336, Train Accuracy: 0.7812, Val Loss: 1.2116, Val Accuracy: 0.7054 Epoch 5799/10000, Train Loss: 1.1315, Train Accuracy: 0.7801, Val Loss: 1.2113, Val Accuracy: 0.7054 Epoch 5800/10000, Train Loss: 1.1419, Train Accuracy: 0.7612, Val Loss: 1.2113, Val Accuracy: 0.7054 Epoch 5801/10000, Train Loss: 1.1347, Train Accuracy: 0.7801, Val Loss: 1.2114, Val Accuracy: 0.7054 Epoch 5802/10000, Train Loss: 1.1228, Train Accuracy: 0.7991, Val Loss: 1.2114, Val Accuracy: 0.7054 Epoch 5803/10000, Train Loss: 1.1181, Train Accuracy: 0.8002, Val Loss: 1.2113, Val Accuracy: 0.7054 Epoch 5804/10000, Train Loss: 1.1265, Train Accuracy: 0.7891, Val Loss: 1.2114, Val Accuracy: 0.7054 Epoch 5805/10000, Train Loss: 1.1394, Train Accuracy: 0.7768, Val Loss: 1.2112, Val Accuracy: 0.7054 Epoch 5806/10000, Train Loss: 1.1213, Train Accuracy: 0.7980, Val Loss: 1.2112, Val Accuracy: 0.7054 Epoch 5807/10000, Train Loss: 1.1343, Train Accuracy: 0.7812, Val Loss: 1.2113, Val Accuracy: 0.7054 Epoch 5808/10000, Train Loss: 1.1303, Train Accuracy: 0.7857, Val Loss: 1.2112, Val Accuracy: 0.7054 Epoch 5809/10000, Train Loss: 1.1251, Train Accuracy: 0.7946, Val Loss: 1.2112, Val Accuracy: 0.7054 Epoch 5810/10000, Train Loss: 1.1209, Train Accuracy: 0.8025, Val Loss: 1.2111, Val Accuracy: 0.7054 Epoch 5811/10000, Train Loss: 1.1180, Train Accuracy: 0.7991, Val Loss: 1.2112, Val Accuracy: 0.7054 Epoch 5812/10000, Train Loss: 1.1279, Train Accuracy: 0.7857, Val Loss: 1.2110, Val Accuracy: 0.7054 Epoch 5813/10000, Train Loss: 1.1229, Train Accuracy: 0.7991, Val Loss: 1.2111, Val Accuracy: 0.7054 Epoch 5814/10000, Train Loss: 1.1259, Train Accuracy: 0.7812, Val Loss: 1.2109, Val Accuracy: 0.7054 Epoch 5815/10000, Train Loss: 1.1352, Train Accuracy: 0.7801, Val Loss: 1.2108, Val Accuracy: 0.7054 Epoch 5816/10000, Train Loss: 1.1317, Train Accuracy: 0.7790, Val Loss: 1.2108, Val Accuracy: 0.7054 Epoch 5817/10000, Train Loss: 1.1364, Train Accuracy: 0.7757, Val Loss: 1.2107, Val Accuracy: 0.7054 Epoch 5818/10000, Train Loss: 1.1192, Train Accuracy: 0.7991, Val Loss: 1.2105, Val Accuracy: 0.7054 Epoch 5819/10000, Train Loss: 1.1299, Train Accuracy: 0.7958, Val Loss: 1.2107, Val Accuracy: 0.7054 Epoch 5820/10000, Train Loss: 1.1260, Train Accuracy: 0.7846, Val Loss: 1.2107, Val Accuracy: 0.7054 Epoch 5821/10000, Train Loss: 1.1354, Train Accuracy: 0.7712, Val Loss: 1.2109, Val Accuracy: 0.7098 Epoch 5822/10000, Train Loss: 1.1231, Train Accuracy: 0.7991, Val Loss: 1.2109, Val Accuracy: 0.7098 Epoch 5823/10000, Train Loss: 1.1373, Train Accuracy: 0.7734, Val Loss: 1.2108, Val Accuracy: 0.7054 Epoch 5824/10000, Train Loss: 1.1216, Train Accuracy: 0.7958, Val Loss: 1.2109, Val Accuracy: 0.7098 Epoch 5825/10000, Train Loss: 1.1273, Train Accuracy: 0.7868, Val Loss: 1.2109, Val Accuracy: 0.7098 Epoch 5826/10000, Train Loss: 1.1181, Train Accuracy: 0.8025, Val Loss: 1.2106, Val Accuracy: 0.7054 Epoch 5827/10000, Train Loss: 1.1279, Train Accuracy: 0.7924, Val Loss: 1.2105, Val Accuracy: 0.7098 Epoch 5828/10000, Train Loss: 1.1386, Train Accuracy: 0.7812, Val Loss: 1.2104, Val Accuracy: 0.7098 Epoch 5829/10000, Train Loss: 1.1303, Train Accuracy: 0.7924, Val Loss: 1.2100, Val Accuracy: 0.7098 Epoch 5830/10000, Train Loss: 1.1265, Train Accuracy: 0.7935, Val Loss: 1.2099, Val Accuracy: 0.7098 Epoch 5831/10000, Train Loss: 1.1280, Train Accuracy: 0.7891, Val Loss: 1.2096, Val Accuracy: 0.7098 Epoch 5832/10000, Train Loss: 1.1245, Train Accuracy: 0.7857, Val Loss: 1.2095, Val Accuracy: 0.7098 Epoch 5833/10000, Train Loss: 1.1300, Train Accuracy: 0.7879, Val Loss: 1.2096, Val Accuracy: 0.7098 Epoch 5834/10000, Train Loss: 1.1337, Train Accuracy: 0.7824, Val Loss: 1.2098, Val Accuracy: 0.7098 Epoch 5835/10000, Train Loss: 1.1393, Train Accuracy: 0.7712, Val Loss: 1.2098, Val Accuracy: 0.7098 Epoch 5836/10000, Train Loss: 1.1224, Train Accuracy: 0.7879, Val Loss: 1.2099, Val Accuracy: 0.7098 Epoch 5837/10000, Train Loss: 1.1276, Train Accuracy: 0.7824, Val Loss: 1.2099, Val Accuracy: 0.7054 Epoch 5838/10000, Train Loss: 1.1300, Train Accuracy: 0.7868, Val Loss: 1.2100, Val Accuracy: 0.7054 Epoch 5839/10000, Train Loss: 1.1314, Train Accuracy: 0.7935, Val Loss: 1.2099, Val Accuracy: 0.7054 Epoch 5840/10000, Train Loss: 1.1201, Train Accuracy: 0.7902, Val Loss: 1.2101, Val Accuracy: 0.7009 Epoch 5841/10000, Train Loss: 1.1257, Train Accuracy: 0.8013, Val Loss: 1.2100, Val Accuracy: 0.7009 Epoch 5842/10000, Train Loss: 1.1230, Train Accuracy: 0.8036, Val Loss: 1.2099, Val Accuracy: 0.7009 Epoch 5843/10000, Train Loss: 1.1207, Train Accuracy: 0.7969, Val Loss: 1.2097, Val Accuracy: 0.7054 Epoch 5844/10000, Train Loss: 1.1271, Train Accuracy: 0.7868, Val Loss: 1.2097, Val Accuracy: 0.7054 Epoch 5845/10000, Train Loss: 1.1212, Train Accuracy: 0.7924, Val Loss: 1.2096, Val Accuracy: 0.7098 Epoch 5846/10000, Train Loss: 1.1298, Train Accuracy: 0.7924, Val Loss: 1.2095, Val Accuracy: 0.7098 Epoch 5847/10000, Train Loss: 1.1309, Train Accuracy: 0.7801, Val Loss: 1.2093, Val Accuracy: 0.7098 Epoch 5848/10000, Train Loss: 1.1325, Train Accuracy: 0.7812, Val Loss: 1.2092, Val Accuracy: 0.7054 Epoch 5849/10000, Train Loss: 1.1218, Train Accuracy: 0.7924, Val Loss: 1.2092, Val Accuracy: 0.7098 Epoch 5850/10000, Train Loss: 1.1189, Train Accuracy: 0.7969, Val Loss: 1.2091, Val Accuracy: 0.7098 Epoch 5851/10000, Train Loss: 1.1283, Train Accuracy: 0.7846, Val Loss: 1.2090, Val Accuracy: 0.7098 Epoch 5852/10000, Train Loss: 1.1276, Train Accuracy: 0.7935, Val Loss: 1.2088, Val Accuracy: 0.7098 Epoch 5853/10000, Train Loss: 1.1310, Train Accuracy: 0.7801, Val Loss: 1.2091, Val Accuracy: 0.7098 Epoch 5854/10000, Train Loss: 1.1329, Train Accuracy: 0.7790, Val Loss: 1.2091, Val Accuracy: 0.7098 Epoch 5855/10000, Train Loss: 1.1459, Train Accuracy: 0.7690, Val Loss: 1.2093, Val Accuracy: 0.7098 Epoch 5856/10000, Train Loss: 1.1202, Train Accuracy: 0.7935, Val Loss: 1.2091, Val Accuracy: 0.7098 Epoch 5857/10000, Train Loss: 1.1190, Train Accuracy: 0.7946, Val Loss: 1.2093, Val Accuracy: 0.7098 Epoch 5858/10000, Train Loss: 1.1248, Train Accuracy: 0.7868, Val Loss: 1.2093, Val Accuracy: 0.7054 Epoch 5859/10000, Train Loss: 1.1257, Train Accuracy: 0.7868, Val Loss: 1.2091, Val Accuracy: 0.7054 Epoch 5860/10000, Train Loss: 1.1355, Train Accuracy: 0.7779, Val Loss: 1.2087, Val Accuracy: 0.7054 Epoch 5861/10000, Train Loss: 1.1174, Train Accuracy: 0.7958, Val Loss: 1.2087, Val Accuracy: 0.7054 Epoch 5862/10000, Train Loss: 1.1190, Train Accuracy: 0.7935, Val Loss: 1.2090, Val Accuracy: 0.7054 Epoch 5863/10000, Train Loss: 1.1387, Train Accuracy: 0.7734, Val Loss: 1.2091, Val Accuracy: 0.7054 Epoch 5864/10000, Train Loss: 1.1298, Train Accuracy: 0.7891, Val Loss: 1.2092, Val Accuracy: 0.7054 Epoch 5865/10000, Train Loss: 1.1384, Train Accuracy: 0.7712, Val Loss: 1.2093, Val Accuracy: 0.7054 Epoch 5866/10000, Train Loss: 1.1255, Train Accuracy: 0.7946, Val Loss: 1.2092, Val Accuracy: 0.7054 Epoch 5867/10000, Train Loss: 1.1273, Train Accuracy: 0.7768, Val Loss: 1.2094, Val Accuracy: 0.7054 Epoch 5868/10000, Train Loss: 1.1259, Train Accuracy: 0.7891, Val Loss: 1.2092, Val Accuracy: 0.7054 Epoch 5869/10000, Train Loss: 1.1241, Train Accuracy: 0.7946, Val Loss: 1.2086, Val Accuracy: 0.7054 Epoch 5870/10000, Train Loss: 1.1283, Train Accuracy: 0.7891, Val Loss: 1.2088, Val Accuracy: 0.7054 Epoch 5871/10000, Train Loss: 1.1250, Train Accuracy: 0.7924, Val Loss: 1.2089, Val Accuracy: 0.7054 Epoch 5872/10000, Train Loss: 1.1365, Train Accuracy: 0.7746, Val Loss: 1.2087, Val Accuracy: 0.7054 Epoch 5873/10000, Train Loss: 1.1336, Train Accuracy: 0.7835, Val Loss: 1.2085, Val Accuracy: 0.7054 Epoch 5874/10000, Train Loss: 1.1299, Train Accuracy: 0.7757, Val Loss: 1.2087, Val Accuracy: 0.7054 Epoch 5875/10000, Train Loss: 1.1331, Train Accuracy: 0.7846, Val Loss: 1.2085, Val Accuracy: 0.7054 Epoch 5876/10000, Train Loss: 1.1332, Train Accuracy: 0.7835, Val Loss: 1.2086, Val Accuracy: 0.7009 Epoch 5877/10000, Train Loss: 1.1164, Train Accuracy: 0.7991, Val Loss: 1.2086, Val Accuracy: 0.7009 Epoch 5878/10000, Train Loss: 1.1229, Train Accuracy: 0.7924, Val Loss: 1.2086, Val Accuracy: 0.7009 Epoch 5879/10000, Train Loss: 1.1191, Train Accuracy: 0.7946, Val Loss: 1.2085, Val Accuracy: 0.7009 Epoch 5880/10000, Train Loss: 1.1188, Train Accuracy: 0.7891, Val Loss: 1.2086, Val Accuracy: 0.7009 Epoch 5881/10000, Train Loss: 1.1398, Train Accuracy: 0.7679, Val Loss: 1.2085, Val Accuracy: 0.7009 Epoch 5882/10000, Train Loss: 1.1195, Train Accuracy: 0.7924, Val Loss: 1.2087, Val Accuracy: 0.7009 Epoch 5883/10000, Train Loss: 1.1240, Train Accuracy: 0.7902, Val Loss: 1.2086, Val Accuracy: 0.7009 Epoch 5884/10000, Train Loss: 1.1303, Train Accuracy: 0.7846, Val Loss: 1.2086, Val Accuracy: 0.7009 Epoch 5885/10000, Train Loss: 1.1361, Train Accuracy: 0.7824, Val Loss: 1.2082, Val Accuracy: 0.7009 Epoch 5886/10000, Train Loss: 1.1117, Train Accuracy: 0.8025, Val Loss: 1.2079, Val Accuracy: 0.7009 Epoch 5887/10000, Train Loss: 1.1271, Train Accuracy: 0.7846, Val Loss: 1.2079, Val Accuracy: 0.7009 Epoch 5888/10000, Train Loss: 1.1277, Train Accuracy: 0.7857, Val Loss: 1.2082, Val Accuracy: 0.7009 Epoch 5889/10000, Train Loss: 1.1315, Train Accuracy: 0.7902, Val Loss: 1.2083, Val Accuracy: 0.7009 Epoch 5890/10000, Train Loss: 1.1238, Train Accuracy: 0.7891, Val Loss: 1.2082, Val Accuracy: 0.7009 Epoch 5891/10000, Train Loss: 1.1215, Train Accuracy: 0.7958, Val Loss: 1.2082, Val Accuracy: 0.7009 Epoch 5892/10000, Train Loss: 1.1299, Train Accuracy: 0.7868, Val Loss: 1.2080, Val Accuracy: 0.7009 Epoch 5893/10000, Train Loss: 1.1318, Train Accuracy: 0.7801, Val Loss: 1.2080, Val Accuracy: 0.7009 Epoch 5894/10000, Train Loss: 1.1390, Train Accuracy: 0.7701, Val Loss: 1.2080, Val Accuracy: 0.7009 Epoch 5895/10000, Train Loss: 1.1249, Train Accuracy: 0.7857, Val Loss: 1.2081, Val Accuracy: 0.7009 Epoch 5896/10000, Train Loss: 1.1290, Train Accuracy: 0.7879, Val Loss: 1.2080, Val Accuracy: 0.7009 Epoch 5897/10000, Train Loss: 1.1402, Train Accuracy: 0.7757, Val Loss: 1.2078, Val Accuracy: 0.7009 Epoch 5898/10000, Train Loss: 1.1359, Train Accuracy: 0.7779, Val Loss: 1.2077, Val Accuracy: 0.7009 Epoch 5899/10000, Train Loss: 1.1252, Train Accuracy: 0.7902, Val Loss: 1.2077, Val Accuracy: 0.7009 Epoch 5900/10000, Train Loss: 1.1154, Train Accuracy: 0.8103, Val Loss: 1.2079, Val Accuracy: 0.7009 Epoch 5901/10000, Train Loss: 1.1350, Train Accuracy: 0.7812, Val Loss: 1.2077, Val Accuracy: 0.7009 Epoch 5902/10000, Train Loss: 1.1390, Train Accuracy: 0.7746, Val Loss: 1.2079, Val Accuracy: 0.7054 Epoch 5903/10000, Train Loss: 1.1165, Train Accuracy: 0.8002, Val Loss: 1.2078, Val Accuracy: 0.7054 Epoch 5904/10000, Train Loss: 1.1309, Train Accuracy: 0.7868, Val Loss: 1.2078, Val Accuracy: 0.7054 Epoch 5905/10000, Train Loss: 1.1223, Train Accuracy: 0.7924, Val Loss: 1.2079, Val Accuracy: 0.7054 Epoch 5906/10000, Train Loss: 1.1209, Train Accuracy: 0.7958, Val Loss: 1.2079, Val Accuracy: 0.7054 Epoch 5907/10000, Train Loss: 1.1290, Train Accuracy: 0.7812, Val Loss: 1.2078, Val Accuracy: 0.7054 Epoch 5908/10000, Train Loss: 1.1227, Train Accuracy: 0.7891, Val Loss: 1.2077, Val Accuracy: 0.7054 Epoch 5909/10000, Train Loss: 1.1233, Train Accuracy: 0.7835, Val Loss: 1.2081, Val Accuracy: 0.7009 Epoch 5910/10000, Train Loss: 1.1292, Train Accuracy: 0.7868, Val Loss: 1.2083, Val Accuracy: 0.7009 Epoch 5911/10000, Train Loss: 1.1190, Train Accuracy: 0.7935, Val Loss: 1.2081, Val Accuracy: 0.7009 Epoch 5912/10000, Train Loss: 1.1298, Train Accuracy: 0.7857, Val Loss: 1.2078, Val Accuracy: 0.7009 Epoch 5913/10000, Train Loss: 1.1231, Train Accuracy: 0.7980, Val Loss: 1.2075, Val Accuracy: 0.7009 Epoch 5914/10000, Train Loss: 1.1179, Train Accuracy: 0.8013, Val Loss: 1.2073, Val Accuracy: 0.7009 Epoch 5915/10000, Train Loss: 1.1174, Train Accuracy: 0.8025, Val Loss: 1.2070, Val Accuracy: 0.7009 Epoch 5916/10000, Train Loss: 1.1165, Train Accuracy: 0.8013, Val Loss: 1.2072, Val Accuracy: 0.7009 Epoch 5917/10000, Train Loss: 1.1265, Train Accuracy: 0.7902, Val Loss: 1.2073, Val Accuracy: 0.7009 Epoch 5918/10000, Train Loss: 1.1171, Train Accuracy: 0.8002, Val Loss: 1.2076, Val Accuracy: 0.7054 Epoch 5919/10000, Train Loss: 1.1239, Train Accuracy: 0.7868, Val Loss: 1.2076, Val Accuracy: 0.7009 Epoch 5920/10000, Train Loss: 1.1276, Train Accuracy: 0.7801, Val Loss: 1.2082, Val Accuracy: 0.7009 Epoch 5921/10000, Train Loss: 1.1327, Train Accuracy: 0.7902, Val Loss: 1.2082, Val Accuracy: 0.7009 Epoch 5922/10000, Train Loss: 1.1173, Train Accuracy: 0.8025, Val Loss: 1.2080, Val Accuracy: 0.7009 Epoch 5923/10000, Train Loss: 1.1256, Train Accuracy: 0.7902, Val Loss: 1.2078, Val Accuracy: 0.7009 Epoch 5924/10000, Train Loss: 1.1240, Train Accuracy: 0.7935, Val Loss: 1.2079, Val Accuracy: 0.7054 Epoch 5925/10000, Train Loss: 1.1209, Train Accuracy: 0.8002, Val Loss: 1.2077, Val Accuracy: 0.7054 Epoch 5926/10000, Train Loss: 1.1182, Train Accuracy: 0.7991, Val Loss: 1.2077, Val Accuracy: 0.7054 Epoch 5927/10000, Train Loss: 1.1263, Train Accuracy: 0.7924, Val Loss: 1.2076, Val Accuracy: 0.7054 Epoch 5928/10000, Train Loss: 1.1266, Train Accuracy: 0.7902, Val Loss: 1.2071, Val Accuracy: 0.7054 Epoch 5929/10000, Train Loss: 1.1275, Train Accuracy: 0.7935, Val Loss: 1.2071, Val Accuracy: 0.7054 Epoch 5930/10000, Train Loss: 1.1295, Train Accuracy: 0.7779, Val Loss: 1.2070, Val Accuracy: 0.7054 Epoch 5931/10000, Train Loss: 1.1128, Train Accuracy: 0.8036, Val Loss: 1.2069, Val Accuracy: 0.7009 Epoch 5932/10000, Train Loss: 1.1217, Train Accuracy: 0.7857, Val Loss: 1.2067, Val Accuracy: 0.7009 Epoch 5933/10000, Train Loss: 1.1120, Train Accuracy: 0.8047, Val Loss: 1.2065, Val Accuracy: 0.7009 Epoch 5934/10000, Train Loss: 1.1245, Train Accuracy: 0.7879, Val Loss: 1.2067, Val Accuracy: 0.7054 Epoch 5935/10000, Train Loss: 1.1276, Train Accuracy: 0.7902, Val Loss: 1.2067, Val Accuracy: 0.7054 Epoch 5936/10000, Train Loss: 1.1305, Train Accuracy: 0.7801, Val Loss: 1.2070, Val Accuracy: 0.7009 Epoch 5937/10000, Train Loss: 1.1157, Train Accuracy: 0.7980, Val Loss: 1.2071, Val Accuracy: 0.7009 Epoch 5938/10000, Train Loss: 1.1287, Train Accuracy: 0.7924, Val Loss: 1.2071, Val Accuracy: 0.7009 Epoch 5939/10000, Train Loss: 1.1138, Train Accuracy: 0.8013, Val Loss: 1.2069, Val Accuracy: 0.7009 Epoch 5940/10000, Train Loss: 1.1233, Train Accuracy: 0.7902, Val Loss: 1.2071, Val Accuracy: 0.7009 Epoch 5941/10000, Train Loss: 1.1115, Train Accuracy: 0.8103, Val Loss: 1.2069, Val Accuracy: 0.7009 Epoch 5942/10000, Train Loss: 1.1200, Train Accuracy: 0.8013, Val Loss: 1.2071, Val Accuracy: 0.7009 Epoch 5943/10000, Train Loss: 1.1225, Train Accuracy: 0.7891, Val Loss: 1.2071, Val Accuracy: 0.7009 Epoch 5944/10000, Train Loss: 1.1372, Train Accuracy: 0.7790, Val Loss: 1.2069, Val Accuracy: 0.7009 Epoch 5945/10000, Train Loss: 1.1204, Train Accuracy: 0.7946, Val Loss: 1.2070, Val Accuracy: 0.7009 Epoch 5946/10000, Train Loss: 1.1139, Train Accuracy: 0.8002, Val Loss: 1.2067, Val Accuracy: 0.7009 Epoch 5947/10000, Train Loss: 1.1235, Train Accuracy: 0.7935, Val Loss: 1.2065, Val Accuracy: 0.7054 Epoch 5948/10000, Train Loss: 1.1096, Train Accuracy: 0.7969, Val Loss: 1.2064, Val Accuracy: 0.7054 Epoch 5949/10000, Train Loss: 1.1281, Train Accuracy: 0.7879, Val Loss: 1.2062, Val Accuracy: 0.7054 Epoch 5950/10000, Train Loss: 1.1287, Train Accuracy: 0.7879, Val Loss: 1.2059, Val Accuracy: 0.7009 Epoch 5951/10000, Train Loss: 1.1273, Train Accuracy: 0.7857, Val Loss: 1.2061, Val Accuracy: 0.7009 Epoch 5952/10000, Train Loss: 1.1235, Train Accuracy: 0.7902, Val Loss: 1.2059, Val Accuracy: 0.7009 Epoch 5953/10000, Train Loss: 1.1290, Train Accuracy: 0.7812, Val Loss: 1.2060, Val Accuracy: 0.7009 Epoch 5954/10000, Train Loss: 1.1222, Train Accuracy: 0.7958, Val Loss: 1.2058, Val Accuracy: 0.7009 Epoch 5955/10000, Train Loss: 1.1196, Train Accuracy: 0.8025, Val Loss: 1.2058, Val Accuracy: 0.7009 Epoch 5956/10000, Train Loss: 1.1218, Train Accuracy: 0.7935, Val Loss: 1.2058, Val Accuracy: 0.7009 Epoch 5957/10000, Train Loss: 1.1258, Train Accuracy: 0.7846, Val Loss: 1.2057, Val Accuracy: 0.7009 Epoch 5958/10000, Train Loss: 1.1240, Train Accuracy: 0.7891, Val Loss: 1.2059, Val Accuracy: 0.7009 Epoch 5959/10000, Train Loss: 1.1329, Train Accuracy: 0.7857, Val Loss: 1.2058, Val Accuracy: 0.7054 Epoch 5960/10000, Train Loss: 1.1283, Train Accuracy: 0.7835, Val Loss: 1.2057, Val Accuracy: 0.7009 Epoch 5961/10000, Train Loss: 1.1265, Train Accuracy: 0.7902, Val Loss: 1.2057, Val Accuracy: 0.7054 Epoch 5962/10000, Train Loss: 1.1192, Train Accuracy: 0.7946, Val Loss: 1.2054, Val Accuracy: 0.7054 Epoch 5963/10000, Train Loss: 1.1237, Train Accuracy: 0.7902, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 5964/10000, Train Loss: 1.1160, Train Accuracy: 0.7958, Val Loss: 1.2054, Val Accuracy: 0.7054 Epoch 5965/10000, Train Loss: 1.1191, Train Accuracy: 0.7891, Val Loss: 1.2057, Val Accuracy: 0.7054 Epoch 5966/10000, Train Loss: 1.1226, Train Accuracy: 0.7958, Val Loss: 1.2058, Val Accuracy: 0.7054 Epoch 5967/10000, Train Loss: 1.1202, Train Accuracy: 0.7946, Val Loss: 1.2055, Val Accuracy: 0.7054 Epoch 5968/10000, Train Loss: 1.1179, Train Accuracy: 0.7980, Val Loss: 1.2055, Val Accuracy: 0.7054 Epoch 5969/10000, Train Loss: 1.1284, Train Accuracy: 0.7913, Val Loss: 1.2051, Val Accuracy: 0.7054 Epoch 5970/10000, Train Loss: 1.1194, Train Accuracy: 0.7924, Val Loss: 1.2049, Val Accuracy: 0.7054 Epoch 5971/10000, Train Loss: 1.1121, Train Accuracy: 0.7946, Val Loss: 1.2051, Val Accuracy: 0.7054 Epoch 5972/10000, Train Loss: 1.1207, Train Accuracy: 0.7935, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 5973/10000, Train Loss: 1.1232, Train Accuracy: 0.7857, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 5974/10000, Train Loss: 1.1261, Train Accuracy: 0.7879, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 5975/10000, Train Loss: 1.1270, Train Accuracy: 0.7868, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 5976/10000, Train Loss: 1.1309, Train Accuracy: 0.7891, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 5977/10000, Train Loss: 1.1244, Train Accuracy: 0.7913, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 5978/10000, Train Loss: 1.1256, Train Accuracy: 0.7846, Val Loss: 1.2054, Val Accuracy: 0.7054 Epoch 5979/10000, Train Loss: 1.1361, Train Accuracy: 0.7746, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 5980/10000, Train Loss: 1.1223, Train Accuracy: 0.7924, Val Loss: 1.2050, Val Accuracy: 0.7054 Epoch 5981/10000, Train Loss: 1.1175, Train Accuracy: 0.7991, Val Loss: 1.2050, Val Accuracy: 0.7054 Epoch 5982/10000, Train Loss: 1.1253, Train Accuracy: 0.7913, Val Loss: 1.2051, Val Accuracy: 0.7054 Epoch 5983/10000, Train Loss: 1.1245, Train Accuracy: 0.7902, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 5984/10000, Train Loss: 1.1115, Train Accuracy: 0.8069, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 5985/10000, Train Loss: 1.1192, Train Accuracy: 0.7980, Val Loss: 1.2050, Val Accuracy: 0.7054 Epoch 5986/10000, Train Loss: 1.1300, Train Accuracy: 0.7801, Val Loss: 1.2047, Val Accuracy: 0.7054 Epoch 5987/10000, Train Loss: 1.1190, Train Accuracy: 0.7935, Val Loss: 1.2050, Val Accuracy: 0.7054 Epoch 5988/10000, Train Loss: 1.1126, Train Accuracy: 0.8036, Val Loss: 1.2049, Val Accuracy: 0.7054 Epoch 5989/10000, Train Loss: 1.1149, Train Accuracy: 0.7980, Val Loss: 1.2052, Val Accuracy: 0.7098 Epoch 5990/10000, Train Loss: 1.1207, Train Accuracy: 0.7891, Val Loss: 1.2050, Val Accuracy: 0.7054 Epoch 5991/10000, Train Loss: 1.1269, Train Accuracy: 0.7902, Val Loss: 1.2052, Val Accuracy: 0.7098 Epoch 5992/10000, Train Loss: 1.1270, Train Accuracy: 0.7879, Val Loss: 1.2051, Val Accuracy: 0.7098 Epoch 5993/10000, Train Loss: 1.1426, Train Accuracy: 0.7690, Val Loss: 1.2050, Val Accuracy: 0.7098 Epoch 5994/10000, Train Loss: 1.1203, Train Accuracy: 0.7958, Val Loss: 1.2049, Val Accuracy: 0.7098 Epoch 5995/10000, Train Loss: 1.1198, Train Accuracy: 0.7980, Val Loss: 1.2049, Val Accuracy: 0.7098 Epoch 5996/10000, Train Loss: 1.1295, Train Accuracy: 0.7812, Val Loss: 1.2051, Val Accuracy: 0.7098 Epoch 5997/10000, Train Loss: 1.1075, Train Accuracy: 0.8080, Val Loss: 1.2049, Val Accuracy: 0.7098 Epoch 5998/10000, Train Loss: 1.1050, Train Accuracy: 0.8125, Val Loss: 1.2047, Val Accuracy: 0.7098 Epoch 5999/10000, Train Loss: 1.1299, Train Accuracy: 0.7835, Val Loss: 1.2047, Val Accuracy: 0.7098 Epoch 6000/10000, Train Loss: 1.1231, Train Accuracy: 0.7924, Val Loss: 1.2046, Val Accuracy: 0.7098 Epoch 6001/10000, Train Loss: 1.1130, Train Accuracy: 0.8047, Val Loss: 1.2047, Val Accuracy: 0.7098 Epoch 6002/10000, Train Loss: 1.1126, Train Accuracy: 0.8069, Val Loss: 1.2049, Val Accuracy: 0.7098 Epoch 6003/10000, Train Loss: 1.1112, Train Accuracy: 0.8080, Val Loss: 1.2047, Val Accuracy: 0.7098 Epoch 6004/10000, Train Loss: 1.1176, Train Accuracy: 0.7891, Val Loss: 1.2047, Val Accuracy: 0.7098 Epoch 6005/10000, Train Loss: 1.1201, Train Accuracy: 0.7946, Val Loss: 1.2047, Val Accuracy: 0.7098 Epoch 6006/10000, Train Loss: 1.1058, Train Accuracy: 0.8136, Val Loss: 1.2049, Val Accuracy: 0.7098 Epoch 6007/10000, Train Loss: 1.1117, Train Accuracy: 0.8013, Val Loss: 1.2048, Val Accuracy: 0.7098 Epoch 6008/10000, Train Loss: 1.1316, Train Accuracy: 0.7857, Val Loss: 1.2048, Val Accuracy: 0.7098 Epoch 6009/10000, Train Loss: 1.1081, Train Accuracy: 0.8136, Val Loss: 1.2048, Val Accuracy: 0.7098 Epoch 6010/10000, Train Loss: 1.1245, Train Accuracy: 0.7857, Val Loss: 1.2046, Val Accuracy: 0.7098 Epoch 6011/10000, Train Loss: 1.1223, Train Accuracy: 0.8002, Val Loss: 1.2050, Val Accuracy: 0.7098 Epoch 6012/10000, Train Loss: 1.1132, Train Accuracy: 0.8092, Val Loss: 1.2048, Val Accuracy: 0.7098 Epoch 6013/10000, Train Loss: 1.1075, Train Accuracy: 0.8069, Val Loss: 1.2051, Val Accuracy: 0.7098 Epoch 6014/10000, Train Loss: 1.1344, Train Accuracy: 0.7768, Val Loss: 1.2054, Val Accuracy: 0.7098 Epoch 6015/10000, Train Loss: 1.1266, Train Accuracy: 0.7868, Val Loss: 1.2054, Val Accuracy: 0.7098 Epoch 6016/10000, Train Loss: 1.1132, Train Accuracy: 0.8114, Val Loss: 1.2054, Val Accuracy: 0.7054 Epoch 6017/10000, Train Loss: 1.1316, Train Accuracy: 0.7824, Val Loss: 1.2055, Val Accuracy: 0.7054 Epoch 6018/10000, Train Loss: 1.1156, Train Accuracy: 0.7991, Val Loss: 1.2055, Val Accuracy: 0.7009 Epoch 6019/10000, Train Loss: 1.1129, Train Accuracy: 0.8080, Val Loss: 1.2056, Val Accuracy: 0.7009 Epoch 6020/10000, Train Loss: 1.1268, Train Accuracy: 0.7801, Val Loss: 1.2054, Val Accuracy: 0.7054 Epoch 6021/10000, Train Loss: 1.1216, Train Accuracy: 0.7891, Val Loss: 1.2055, Val Accuracy: 0.7054 Epoch 6022/10000, Train Loss: 1.1082, Train Accuracy: 0.8114, Val Loss: 1.2057, Val Accuracy: 0.6964 Epoch 6023/10000, Train Loss: 1.1214, Train Accuracy: 0.7946, Val Loss: 1.2052, Val Accuracy: 0.7009 Epoch 6024/10000, Train Loss: 1.1274, Train Accuracy: 0.7879, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 6025/10000, Train Loss: 1.1228, Train Accuracy: 0.7857, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 6026/10000, Train Loss: 1.1206, Train Accuracy: 0.7946, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 6027/10000, Train Loss: 1.1167, Train Accuracy: 0.8036, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 6028/10000, Train Loss: 1.1304, Train Accuracy: 0.7790, Val Loss: 1.2056, Val Accuracy: 0.7054 Epoch 6029/10000, Train Loss: 1.1222, Train Accuracy: 0.7879, Val Loss: 1.2058, Val Accuracy: 0.7009 Epoch 6030/10000, Train Loss: 1.1166, Train Accuracy: 0.8069, Val Loss: 1.2055, Val Accuracy: 0.7009 Epoch 6031/10000, Train Loss: 1.1294, Train Accuracy: 0.7846, Val Loss: 1.2056, Val Accuracy: 0.7009 Epoch 6032/10000, Train Loss: 1.1129, Train Accuracy: 0.8025, Val Loss: 1.2056, Val Accuracy: 0.7054 Epoch 6033/10000, Train Loss: 1.1237, Train Accuracy: 0.7790, Val Loss: 1.2057, Val Accuracy: 0.7009 Epoch 6034/10000, Train Loss: 1.1176, Train Accuracy: 0.7902, Val Loss: 1.2057, Val Accuracy: 0.7054 Epoch 6035/10000, Train Loss: 1.1149, Train Accuracy: 0.7958, Val Loss: 1.2055, Val Accuracy: 0.7054 Epoch 6036/10000, Train Loss: 1.1224, Train Accuracy: 0.7868, Val Loss: 1.2054, Val Accuracy: 0.7054 Epoch 6037/10000, Train Loss: 1.1155, Train Accuracy: 0.8058, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 6038/10000, Train Loss: 1.1109, Train Accuracy: 0.8092, Val Loss: 1.2053, Val Accuracy: 0.7054 Epoch 6039/10000, Train Loss: 1.1188, Train Accuracy: 0.8025, Val Loss: 1.2051, Val Accuracy: 0.7054 Epoch 6040/10000, Train Loss: 1.1082, Train Accuracy: 0.8181, Val Loss: 1.2048, Val Accuracy: 0.7054 Epoch 6041/10000, Train Loss: 1.1199, Train Accuracy: 0.7991, Val Loss: 1.2050, Val Accuracy: 0.7009 Epoch 6042/10000, Train Loss: 1.1155, Train Accuracy: 0.7969, Val Loss: 1.2051, Val Accuracy: 0.7009 Epoch 6043/10000, Train Loss: 1.1104, Train Accuracy: 0.8114, Val Loss: 1.2052, Val Accuracy: 0.7054 Epoch 6044/10000, Train Loss: 1.1259, Train Accuracy: 0.7879, Val Loss: 1.2049, Val Accuracy: 0.7054 Epoch 6045/10000, Train Loss: 1.1221, Train Accuracy: 0.7935, Val Loss: 1.2049, Val Accuracy: 0.7054 Epoch 6046/10000, Train Loss: 1.1079, Train Accuracy: 0.8170, Val Loss: 1.2049, Val Accuracy: 0.7098 Epoch 6047/10000, Train Loss: 1.1141, Train Accuracy: 0.8025, Val Loss: 1.2049, Val Accuracy: 0.7054 Epoch 6048/10000, Train Loss: 1.1155, Train Accuracy: 0.8002, Val Loss: 1.2049, Val Accuracy: 0.7054 Epoch 6049/10000, Train Loss: 1.1306, Train Accuracy: 0.7779, Val Loss: 1.2050, Val Accuracy: 0.7009 Epoch 6050/10000, Train Loss: 1.1190, Train Accuracy: 0.7913, Val Loss: 1.2048, Val Accuracy: 0.7009 Epoch 6051/10000, Train Loss: 1.1152, Train Accuracy: 0.8058, Val Loss: 1.2049, Val Accuracy: 0.7009 Epoch 6052/10000, Train Loss: 1.1135, Train Accuracy: 0.8013, Val Loss: 1.2049, Val Accuracy: 0.7009 Epoch 6053/10000, Train Loss: 1.1275, Train Accuracy: 0.7846, Val Loss: 1.2047, Val Accuracy: 0.7054 Epoch 6054/10000, Train Loss: 1.1214, Train Accuracy: 0.7935, Val Loss: 1.2047, Val Accuracy: 0.7009 Epoch 6055/10000, Train Loss: 1.1248, Train Accuracy: 0.7879, Val Loss: 1.2046, Val Accuracy: 0.7054 Epoch 6056/10000, Train Loss: 1.1104, Train Accuracy: 0.8092, Val Loss: 1.2046, Val Accuracy: 0.7054 Epoch 6057/10000, Train Loss: 1.1100, Train Accuracy: 0.8158, Val Loss: 1.2043, Val Accuracy: 0.7143 Epoch 6058/10000, Train Loss: 1.1202, Train Accuracy: 0.7902, Val Loss: 1.2045, Val Accuracy: 0.7098 Epoch 6059/10000, Train Loss: 1.1208, Train Accuracy: 0.7913, Val Loss: 1.2045, Val Accuracy: 0.7098 Epoch 6060/10000, Train Loss: 1.1247, Train Accuracy: 0.7913, Val Loss: 1.2044, Val Accuracy: 0.7054 Epoch 6061/10000, Train Loss: 1.1107, Train Accuracy: 0.8103, Val Loss: 1.2043, Val Accuracy: 0.7054 Epoch 6062/10000, Train Loss: 1.1166, Train Accuracy: 0.8002, Val Loss: 1.2042, Val Accuracy: 0.7054 Epoch 6063/10000, Train Loss: 1.1037, Train Accuracy: 0.8170, Val Loss: 1.2042, Val Accuracy: 0.7054 Epoch 6064/10000, Train Loss: 1.1085, Train Accuracy: 0.8147, Val Loss: 1.2043, Val Accuracy: 0.7054 Epoch 6065/10000, Train Loss: 1.1211, Train Accuracy: 0.8002, Val Loss: 1.2042, Val Accuracy: 0.7054 Epoch 6066/10000, Train Loss: 1.1285, Train Accuracy: 0.7768, Val Loss: 1.2043, Val Accuracy: 0.7054 Epoch 6067/10000, Train Loss: 1.1169, Train Accuracy: 0.7924, Val Loss: 1.2042, Val Accuracy: 0.7054 Epoch 6068/10000, Train Loss: 1.1148, Train Accuracy: 0.7946, Val Loss: 1.2041, Val Accuracy: 0.7054 Epoch 6069/10000, Train Loss: 1.1178, Train Accuracy: 0.8002, Val Loss: 1.2044, Val Accuracy: 0.7054 Epoch 6070/10000, Train Loss: 1.1177, Train Accuracy: 0.7969, Val Loss: 1.2049, Val Accuracy: 0.7009 Epoch 6071/10000, Train Loss: 1.1167, Train Accuracy: 0.8047, Val Loss: 1.2050, Val Accuracy: 0.6964 Epoch 6072/10000, Train Loss: 1.1139, Train Accuracy: 0.8047, Val Loss: 1.2048, Val Accuracy: 0.7009 Epoch 6073/10000, Train Loss: 1.1227, Train Accuracy: 0.7924, Val Loss: 1.2047, Val Accuracy: 0.7009 Epoch 6074/10000, Train Loss: 1.1341, Train Accuracy: 0.7757, Val Loss: 1.2047, Val Accuracy: 0.7054 Epoch 6075/10000, Train Loss: 1.1182, Train Accuracy: 0.8013, Val Loss: 1.2044, Val Accuracy: 0.7054 Epoch 6076/10000, Train Loss: 1.1096, Train Accuracy: 0.8036, Val Loss: 1.2045, Val Accuracy: 0.7054 Epoch 6077/10000, Train Loss: 1.1227, Train Accuracy: 0.7958, Val Loss: 1.2044, Val Accuracy: 0.7054 Epoch 6078/10000, Train Loss: 1.1176, Train Accuracy: 0.8080, Val Loss: 1.2041, Val Accuracy: 0.7054 Epoch 6079/10000, Train Loss: 1.1201, Train Accuracy: 0.7879, Val Loss: 1.2040, Val Accuracy: 0.7098 Epoch 6080/10000, Train Loss: 1.1171, Train Accuracy: 0.8025, Val Loss: 1.2039, Val Accuracy: 0.7098 Epoch 6081/10000, Train Loss: 1.1163, Train Accuracy: 0.8036, Val Loss: 1.2036, Val Accuracy: 0.7054 Epoch 6082/10000, Train Loss: 1.1147, Train Accuracy: 0.7924, Val Loss: 1.2033, Val Accuracy: 0.7098 Epoch 6083/10000, Train Loss: 1.1227, Train Accuracy: 0.7935, Val Loss: 1.2031, Val Accuracy: 0.7054 Epoch 6084/10000, Train Loss: 1.1220, Train Accuracy: 0.7935, Val Loss: 1.2031, Val Accuracy: 0.7098 Epoch 6085/10000, Train Loss: 1.1121, Train Accuracy: 0.8058, Val Loss: 1.2032, Val Accuracy: 0.7054 Epoch 6086/10000, Train Loss: 1.1169, Train Accuracy: 0.7913, Val Loss: 1.2029, Val Accuracy: 0.7054 Epoch 6087/10000, Train Loss: 1.1155, Train Accuracy: 0.8025, Val Loss: 1.2029, Val Accuracy: 0.7098 Epoch 6088/10000, Train Loss: 1.1214, Train Accuracy: 0.7991, Val Loss: 1.2031, Val Accuracy: 0.7098 Epoch 6089/10000, Train Loss: 1.1148, Train Accuracy: 0.7946, Val Loss: 1.2032, Val Accuracy: 0.7054 Epoch 6090/10000, Train Loss: 1.1091, Train Accuracy: 0.8147, Val Loss: 1.2034, Val Accuracy: 0.7054 Epoch 6091/10000, Train Loss: 1.1234, Train Accuracy: 0.7946, Val Loss: 1.2035, Val Accuracy: 0.7009 Epoch 6092/10000, Train Loss: 1.1207, Train Accuracy: 0.7946, Val Loss: 1.2033, Val Accuracy: 0.7054 Epoch 6093/10000, Train Loss: 1.1140, Train Accuracy: 0.8092, Val Loss: 1.2033, Val Accuracy: 0.7143 Epoch 6094/10000, Train Loss: 1.1311, Train Accuracy: 0.7824, Val Loss: 1.2034, Val Accuracy: 0.7098 Epoch 6095/10000, Train Loss: 1.1165, Train Accuracy: 0.8047, Val Loss: 1.2036, Val Accuracy: 0.7054 Epoch 6096/10000, Train Loss: 1.1193, Train Accuracy: 0.8013, Val Loss: 1.2033, Val Accuracy: 0.7054 Epoch 6097/10000, Train Loss: 1.1350, Train Accuracy: 0.7801, Val Loss: 1.2034, Val Accuracy: 0.7054 Epoch 6098/10000, Train Loss: 1.1161, Train Accuracy: 0.7879, Val Loss: 1.2031, Val Accuracy: 0.7054 Epoch 6099/10000, Train Loss: 1.1048, Train Accuracy: 0.8058, Val Loss: 1.2032, Val Accuracy: 0.7054 Epoch 6100/10000, Train Loss: 1.1226, Train Accuracy: 0.7913, Val Loss: 1.2031, Val Accuracy: 0.7054 Epoch 6101/10000, Train Loss: 1.1181, Train Accuracy: 0.8013, Val Loss: 1.2031, Val Accuracy: 0.7098 Epoch 6102/10000, Train Loss: 1.1266, Train Accuracy: 0.7812, Val Loss: 1.2031, Val Accuracy: 0.7054 Epoch 6103/10000, Train Loss: 1.0969, Train Accuracy: 0.8170, Val Loss: 1.2031, Val Accuracy: 0.7009 Epoch 6104/10000, Train Loss: 1.1197, Train Accuracy: 0.7913, Val Loss: 1.2030, Val Accuracy: 0.7009 Epoch 6105/10000, Train Loss: 1.1065, Train Accuracy: 0.8103, Val Loss: 1.2026, Val Accuracy: 0.7054 Epoch 6106/10000, Train Loss: 1.1121, Train Accuracy: 0.7958, Val Loss: 1.2025, Val Accuracy: 0.7098 Epoch 6107/10000, Train Loss: 1.1089, Train Accuracy: 0.8025, Val Loss: 1.2023, Val Accuracy: 0.7054 Epoch 6108/10000, Train Loss: 1.1247, Train Accuracy: 0.7835, Val Loss: 1.2024, Val Accuracy: 0.7054 Epoch 6109/10000, Train Loss: 1.1013, Train Accuracy: 0.8214, Val Loss: 1.2021, Val Accuracy: 0.7054 Epoch 6110/10000, Train Loss: 1.1248, Train Accuracy: 0.7935, Val Loss: 1.2022, Val Accuracy: 0.7054 Epoch 6111/10000, Train Loss: 1.1231, Train Accuracy: 0.7891, Val Loss: 1.2021, Val Accuracy: 0.7054 Epoch 6112/10000, Train Loss: 1.1207, Train Accuracy: 0.7913, Val Loss: 1.2020, Val Accuracy: 0.7054 Epoch 6113/10000, Train Loss: 1.1162, Train Accuracy: 0.7969, Val Loss: 1.2021, Val Accuracy: 0.7054 Epoch 6114/10000, Train Loss: 1.1180, Train Accuracy: 0.7969, Val Loss: 1.2022, Val Accuracy: 0.7054 Epoch 6115/10000, Train Loss: 1.1172, Train Accuracy: 0.7969, Val Loss: 1.2023, Val Accuracy: 0.7098 Epoch 6116/10000, Train Loss: 1.1032, Train Accuracy: 0.8203, Val Loss: 1.2023, Val Accuracy: 0.7143 Epoch 6117/10000, Train Loss: 1.1204, Train Accuracy: 0.7935, Val Loss: 1.2018, Val Accuracy: 0.7143 Epoch 6118/10000, Train Loss: 1.1125, Train Accuracy: 0.8080, Val Loss: 1.2019, Val Accuracy: 0.7143 Epoch 6119/10000, Train Loss: 1.1145, Train Accuracy: 0.8047, Val Loss: 1.2020, Val Accuracy: 0.7143 Epoch 6120/10000, Train Loss: 1.1087, Train Accuracy: 0.8036, Val Loss: 1.2019, Val Accuracy: 0.7098 Epoch 6121/10000, Train Loss: 1.1204, Train Accuracy: 0.7980, Val Loss: 1.2018, Val Accuracy: 0.7143 Epoch 6122/10000, Train Loss: 1.1093, Train Accuracy: 0.8047, Val Loss: 1.2017, Val Accuracy: 0.7143 Epoch 6123/10000, Train Loss: 1.1203, Train Accuracy: 0.7891, Val Loss: 1.2016, Val Accuracy: 0.7143 Epoch 6124/10000, Train Loss: 1.1246, Train Accuracy: 0.7879, Val Loss: 1.2015, Val Accuracy: 0.7143 Epoch 6125/10000, Train Loss: 1.1214, Train Accuracy: 0.7857, Val Loss: 1.2013, Val Accuracy: 0.7143 Epoch 6126/10000, Train Loss: 1.1152, Train Accuracy: 0.7969, Val Loss: 1.2013, Val Accuracy: 0.7143 Epoch 6127/10000, Train Loss: 1.1251, Train Accuracy: 0.7902, Val Loss: 1.2012, Val Accuracy: 0.7143 Epoch 6128/10000, Train Loss: 1.1163, Train Accuracy: 0.7969, Val Loss: 1.2010, Val Accuracy: 0.7143 Epoch 6129/10000, Train Loss: 1.1422, Train Accuracy: 0.7645, Val Loss: 1.2012, Val Accuracy: 0.7143 Epoch 6130/10000, Train Loss: 1.1139, Train Accuracy: 0.8013, Val Loss: 1.2011, Val Accuracy: 0.7143 Epoch 6131/10000, Train Loss: 1.1238, Train Accuracy: 0.7913, Val Loss: 1.2012, Val Accuracy: 0.7143 Epoch 6132/10000, Train Loss: 1.1269, Train Accuracy: 0.7812, Val Loss: 1.2013, Val Accuracy: 0.7143 Epoch 6133/10000, Train Loss: 1.1190, Train Accuracy: 0.7980, Val Loss: 1.2012, Val Accuracy: 0.7143 Epoch 6134/10000, Train Loss: 1.1076, Train Accuracy: 0.8080, Val Loss: 1.2014, Val Accuracy: 0.7143 Epoch 6135/10000, Train Loss: 1.1323, Train Accuracy: 0.7846, Val Loss: 1.2013, Val Accuracy: 0.7143 Epoch 6136/10000, Train Loss: 1.1225, Train Accuracy: 0.7835, Val Loss: 1.2013, Val Accuracy: 0.7143 Epoch 6137/10000, Train Loss: 1.1129, Train Accuracy: 0.8080, Val Loss: 1.2010, Val Accuracy: 0.7143 Epoch 6138/10000, Train Loss: 1.1023, Train Accuracy: 0.8114, Val Loss: 1.2008, Val Accuracy: 0.7143 Epoch 6139/10000, Train Loss: 1.1055, Train Accuracy: 0.8192, Val Loss: 1.2004, Val Accuracy: 0.7143 Epoch 6140/10000, Train Loss: 1.1166, Train Accuracy: 0.7980, Val Loss: 1.2003, Val Accuracy: 0.7098 Epoch 6141/10000, Train Loss: 1.1245, Train Accuracy: 0.7946, Val Loss: 1.2005, Val Accuracy: 0.7098 Epoch 6142/10000, Train Loss: 1.1254, Train Accuracy: 0.7868, Val Loss: 1.2003, Val Accuracy: 0.7054 Epoch 6143/10000, Train Loss: 1.1312, Train Accuracy: 0.7812, Val Loss: 1.2003, Val Accuracy: 0.7054 Epoch 6144/10000, Train Loss: 1.1166, Train Accuracy: 0.8002, Val Loss: 1.2002, Val Accuracy: 0.7098 Epoch 6145/10000, Train Loss: 1.1232, Train Accuracy: 0.7812, Val Loss: 1.2002, Val Accuracy: 0.7143 Epoch 6146/10000, Train Loss: 1.1148, Train Accuracy: 0.8036, Val Loss: 1.2001, Val Accuracy: 0.7143 Epoch 6147/10000, Train Loss: 1.1101, Train Accuracy: 0.8092, Val Loss: 1.1998, Val Accuracy: 0.7098 Epoch 6148/10000, Train Loss: 1.1161, Train Accuracy: 0.7980, Val Loss: 1.1999, Val Accuracy: 0.7098 Epoch 6149/10000, Train Loss: 1.1074, Train Accuracy: 0.8080, Val Loss: 1.1997, Val Accuracy: 0.7098 Epoch 6150/10000, Train Loss: 1.1079, Train Accuracy: 0.8125, Val Loss: 1.1996, Val Accuracy: 0.7098 Epoch 6151/10000, Train Loss: 1.1131, Train Accuracy: 0.8047, Val Loss: 1.1997, Val Accuracy: 0.7098 Epoch 6152/10000, Train Loss: 1.1103, Train Accuracy: 0.8069, Val Loss: 1.1996, Val Accuracy: 0.7098 Epoch 6153/10000, Train Loss: 1.1217, Train Accuracy: 0.7812, Val Loss: 1.1999, Val Accuracy: 0.7098 Epoch 6154/10000, Train Loss: 1.1223, Train Accuracy: 0.7891, Val Loss: 1.2001, Val Accuracy: 0.7098 Epoch 6155/10000, Train Loss: 1.1164, Train Accuracy: 0.8047, Val Loss: 1.2002, Val Accuracy: 0.7098 Epoch 6156/10000, Train Loss: 1.1190, Train Accuracy: 0.7924, Val Loss: 1.2001, Val Accuracy: 0.7098 Epoch 6157/10000, Train Loss: 1.1137, Train Accuracy: 0.8002, Val Loss: 1.1999, Val Accuracy: 0.7098 Epoch 6158/10000, Train Loss: 1.1170, Train Accuracy: 0.7980, Val Loss: 1.1996, Val Accuracy: 0.7143 Epoch 6159/10000, Train Loss: 1.1145, Train Accuracy: 0.8092, Val Loss: 1.1995, Val Accuracy: 0.7188 Epoch 6160/10000, Train Loss: 1.1209, Train Accuracy: 0.7935, Val Loss: 1.1995, Val Accuracy: 0.7188 Epoch 6161/10000, Train Loss: 1.1167, Train Accuracy: 0.8047, Val Loss: 1.1993, Val Accuracy: 0.7188 Epoch 6162/10000, Train Loss: 1.1128, Train Accuracy: 0.8047, Val Loss: 1.1995, Val Accuracy: 0.7143 Epoch 6163/10000, Train Loss: 1.1147, Train Accuracy: 0.7958, Val Loss: 1.1995, Val Accuracy: 0.7143 Epoch 6164/10000, Train Loss: 1.1162, Train Accuracy: 0.8013, Val Loss: 1.1993, Val Accuracy: 0.7143 Epoch 6165/10000, Train Loss: 1.1100, Train Accuracy: 0.8058, Val Loss: 1.1991, Val Accuracy: 0.7143 Epoch 6166/10000, Train Loss: 1.1143, Train Accuracy: 0.8013, Val Loss: 1.1992, Val Accuracy: 0.7143 Epoch 6167/10000, Train Loss: 1.1217, Train Accuracy: 0.7913, Val Loss: 1.1990, Val Accuracy: 0.7143 Epoch 6168/10000, Train Loss: 1.1180, Train Accuracy: 0.7958, Val Loss: 1.1992, Val Accuracy: 0.7143 Epoch 6169/10000, Train Loss: 1.1066, Train Accuracy: 0.8092, Val Loss: 1.1989, Val Accuracy: 0.7143 Epoch 6170/10000, Train Loss: 1.1197, Train Accuracy: 0.7980, Val Loss: 1.1989, Val Accuracy: 0.7143 Epoch 6171/10000, Train Loss: 1.1133, Train Accuracy: 0.7991, Val Loss: 1.1987, Val Accuracy: 0.7098 Epoch 6172/10000, Train Loss: 1.1152, Train Accuracy: 0.7924, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6173/10000, Train Loss: 1.1147, Train Accuracy: 0.7991, Val Loss: 1.1990, Val Accuracy: 0.7098 Epoch 6174/10000, Train Loss: 1.1006, Train Accuracy: 0.8170, Val Loss: 1.1993, Val Accuracy: 0.7098 Epoch 6175/10000, Train Loss: 1.1176, Train Accuracy: 0.7946, Val Loss: 1.1995, Val Accuracy: 0.7143 Epoch 6176/10000, Train Loss: 1.1167, Train Accuracy: 0.7969, Val Loss: 1.1992, Val Accuracy: 0.7188 Epoch 6177/10000, Train Loss: 1.1092, Train Accuracy: 0.8036, Val Loss: 1.1989, Val Accuracy: 0.7143 Epoch 6178/10000, Train Loss: 1.1096, Train Accuracy: 0.8092, Val Loss: 1.1991, Val Accuracy: 0.7143 Epoch 6179/10000, Train Loss: 1.1118, Train Accuracy: 0.8036, Val Loss: 1.1990, Val Accuracy: 0.7143 Epoch 6180/10000, Train Loss: 1.1154, Train Accuracy: 0.7980, Val Loss: 1.1990, Val Accuracy: 0.7188 Epoch 6181/10000, Train Loss: 1.1057, Train Accuracy: 0.8136, Val Loss: 1.1991, Val Accuracy: 0.7188 Epoch 6182/10000, Train Loss: 1.1180, Train Accuracy: 0.8047, Val Loss: 1.1991, Val Accuracy: 0.7188 Epoch 6183/10000, Train Loss: 1.1244, Train Accuracy: 0.7868, Val Loss: 1.1991, Val Accuracy: 0.7188 Epoch 6184/10000, Train Loss: 1.1150, Train Accuracy: 0.8058, Val Loss: 1.1993, Val Accuracy: 0.7143 Epoch 6185/10000, Train Loss: 1.1054, Train Accuracy: 0.8114, Val Loss: 1.1992, Val Accuracy: 0.7143 Epoch 6186/10000, Train Loss: 1.1177, Train Accuracy: 0.7958, Val Loss: 1.1990, Val Accuracy: 0.7188 Epoch 6187/10000, Train Loss: 1.1131, Train Accuracy: 0.8002, Val Loss: 1.1990, Val Accuracy: 0.7143 Epoch 6188/10000, Train Loss: 1.1133, Train Accuracy: 0.8002, Val Loss: 1.1990, Val Accuracy: 0.7188 Epoch 6189/10000, Train Loss: 1.1077, Train Accuracy: 0.8092, Val Loss: 1.1988, Val Accuracy: 0.7143 Epoch 6190/10000, Train Loss: 1.1102, Train Accuracy: 0.8013, Val Loss: 1.1989, Val Accuracy: 0.7188 Epoch 6191/10000, Train Loss: 1.1190, Train Accuracy: 0.7958, Val Loss: 1.1990, Val Accuracy: 0.7143 Epoch 6192/10000, Train Loss: 1.1152, Train Accuracy: 0.8092, Val Loss: 1.1988, Val Accuracy: 0.7098 Epoch 6193/10000, Train Loss: 1.1143, Train Accuracy: 0.7946, Val Loss: 1.1988, Val Accuracy: 0.7098 Epoch 6194/10000, Train Loss: 1.1203, Train Accuracy: 0.7946, Val Loss: 1.1990, Val Accuracy: 0.7054 Epoch 6195/10000, Train Loss: 1.1194, Train Accuracy: 0.7924, Val Loss: 1.1990, Val Accuracy: 0.7098 Epoch 6196/10000, Train Loss: 1.1240, Train Accuracy: 0.7913, Val Loss: 1.1988, Val Accuracy: 0.7098 Epoch 6197/10000, Train Loss: 1.1079, Train Accuracy: 0.8047, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6198/10000, Train Loss: 1.0991, Train Accuracy: 0.8136, Val Loss: 1.1991, Val Accuracy: 0.7098 Epoch 6199/10000, Train Loss: 1.1151, Train Accuracy: 0.7958, Val Loss: 1.1991, Val Accuracy: 0.7143 Epoch 6200/10000, Train Loss: 1.1164, Train Accuracy: 0.8013, Val Loss: 1.1988, Val Accuracy: 0.7143 Epoch 6201/10000, Train Loss: 1.1127, Train Accuracy: 0.8013, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6202/10000, Train Loss: 1.1055, Train Accuracy: 0.8103, Val Loss: 1.1990, Val Accuracy: 0.7143 Epoch 6203/10000, Train Loss: 1.1140, Train Accuracy: 0.8047, Val Loss: 1.1990, Val Accuracy: 0.7143 Epoch 6204/10000, Train Loss: 1.1120, Train Accuracy: 0.7935, Val Loss: 1.1995, Val Accuracy: 0.7143 Epoch 6205/10000, Train Loss: 1.1023, Train Accuracy: 0.8125, Val Loss: 1.1994, Val Accuracy: 0.7098 Epoch 6206/10000, Train Loss: 1.1186, Train Accuracy: 0.7991, Val Loss: 1.1994, Val Accuracy: 0.7054 Epoch 6207/10000, Train Loss: 1.1084, Train Accuracy: 0.8047, Val Loss: 1.1996, Val Accuracy: 0.7054 Epoch 6208/10000, Train Loss: 1.1037, Train Accuracy: 0.8069, Val Loss: 1.1995, Val Accuracy: 0.7098 Epoch 6209/10000, Train Loss: 1.1267, Train Accuracy: 0.7812, Val Loss: 1.1995, Val Accuracy: 0.7098 Epoch 6210/10000, Train Loss: 1.1144, Train Accuracy: 0.8069, Val Loss: 1.1997, Val Accuracy: 0.7098 Epoch 6211/10000, Train Loss: 1.1137, Train Accuracy: 0.7980, Val Loss: 1.1997, Val Accuracy: 0.7098 Epoch 6212/10000, Train Loss: 1.1119, Train Accuracy: 0.8047, Val Loss: 1.1998, Val Accuracy: 0.7098 Epoch 6213/10000, Train Loss: 1.1152, Train Accuracy: 0.7924, Val Loss: 1.1996, Val Accuracy: 0.7143 Epoch 6214/10000, Train Loss: 1.1068, Train Accuracy: 0.8047, Val Loss: 1.1996, Val Accuracy: 0.7143 Epoch 6215/10000, Train Loss: 1.1144, Train Accuracy: 0.8025, Val Loss: 1.1995, Val Accuracy: 0.7098 Epoch 6216/10000, Train Loss: 1.1174, Train Accuracy: 0.7958, Val Loss: 1.1995, Val Accuracy: 0.7098 Epoch 6217/10000, Train Loss: 1.1167, Train Accuracy: 0.7969, Val Loss: 1.1996, Val Accuracy: 0.7098 Epoch 6218/10000, Train Loss: 1.1148, Train Accuracy: 0.7980, Val Loss: 1.1998, Val Accuracy: 0.7143 Epoch 6219/10000, Train Loss: 1.1221, Train Accuracy: 0.7958, Val Loss: 1.1996, Val Accuracy: 0.7098 Epoch 6220/10000, Train Loss: 1.1183, Train Accuracy: 0.7857, Val Loss: 1.1993, Val Accuracy: 0.7098 Epoch 6221/10000, Train Loss: 1.1125, Train Accuracy: 0.7991, Val Loss: 1.1991, Val Accuracy: 0.7098 Epoch 6222/10000, Train Loss: 1.1138, Train Accuracy: 0.8036, Val Loss: 1.1990, Val Accuracy: 0.7098 Epoch 6223/10000, Train Loss: 1.1174, Train Accuracy: 0.8002, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6224/10000, Train Loss: 1.1191, Train Accuracy: 0.7958, Val Loss: 1.1987, Val Accuracy: 0.7098 Epoch 6225/10000, Train Loss: 1.1255, Train Accuracy: 0.7835, Val Loss: 1.1988, Val Accuracy: 0.7098 Epoch 6226/10000, Train Loss: 1.1117, Train Accuracy: 0.7969, Val Loss: 1.1987, Val Accuracy: 0.7098 Epoch 6227/10000, Train Loss: 1.1149, Train Accuracy: 0.8036, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6228/10000, Train Loss: 1.1100, Train Accuracy: 0.8013, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6229/10000, Train Loss: 1.1099, Train Accuracy: 0.8080, Val Loss: 1.1989, Val Accuracy: 0.7098 Epoch 6230/10000, Train Loss: 1.1144, Train Accuracy: 0.8036, Val Loss: 1.1986, Val Accuracy: 0.7098 Epoch 6231/10000, Train Loss: 1.1093, Train Accuracy: 0.8103, Val Loss: 1.1981, Val Accuracy: 0.7098 Epoch 6232/10000, Train Loss: 1.1077, Train Accuracy: 0.8069, Val Loss: 1.1982, Val Accuracy: 0.7098 Epoch 6233/10000, Train Loss: 1.1245, Train Accuracy: 0.7868, Val Loss: 1.1978, Val Accuracy: 0.7143 Epoch 6234/10000, Train Loss: 1.1078, Train Accuracy: 0.8047, Val Loss: 1.1982, Val Accuracy: 0.7143 Epoch 6235/10000, Train Loss: 1.1182, Train Accuracy: 0.7924, Val Loss: 1.1980, Val Accuracy: 0.7098 Epoch 6236/10000, Train Loss: 1.1054, Train Accuracy: 0.8114, Val Loss: 1.1982, Val Accuracy: 0.7143 Epoch 6237/10000, Train Loss: 1.1025, Train Accuracy: 0.8092, Val Loss: 1.1982, Val Accuracy: 0.7143 Epoch 6238/10000, Train Loss: 1.1287, Train Accuracy: 0.7779, Val Loss: 1.1980, Val Accuracy: 0.7098 Epoch 6239/10000, Train Loss: 1.1081, Train Accuracy: 0.8103, Val Loss: 1.1980, Val Accuracy: 0.7098 Epoch 6240/10000, Train Loss: 1.1008, Train Accuracy: 0.8080, Val Loss: 1.1978, Val Accuracy: 0.7098 Epoch 6241/10000, Train Loss: 1.1081, Train Accuracy: 0.8069, Val Loss: 1.1977, Val Accuracy: 0.7098 Epoch 6242/10000, Train Loss: 1.1117, Train Accuracy: 0.8036, Val Loss: 1.1978, Val Accuracy: 0.7098 Epoch 6243/10000, Train Loss: 1.1213, Train Accuracy: 0.7812, Val Loss: 1.1977, Val Accuracy: 0.7098 Epoch 6244/10000, Train Loss: 1.1041, Train Accuracy: 0.8136, Val Loss: 1.1976, Val Accuracy: 0.7098 Epoch 6245/10000, Train Loss: 1.1223, Train Accuracy: 0.7891, Val Loss: 1.1977, Val Accuracy: 0.7098 Epoch 6246/10000, Train Loss: 1.1074, Train Accuracy: 0.8047, Val Loss: 1.1978, Val Accuracy: 0.7098 Epoch 6247/10000, Train Loss: 1.1171, Train Accuracy: 0.7879, Val Loss: 1.1977, Val Accuracy: 0.7098 Epoch 6248/10000, Train Loss: 1.0991, Train Accuracy: 0.8158, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6249/10000, Train Loss: 1.1128, Train Accuracy: 0.8013, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6250/10000, Train Loss: 1.1241, Train Accuracy: 0.7902, Val Loss: 1.1976, Val Accuracy: 0.7054 Epoch 6251/10000, Train Loss: 1.1169, Train Accuracy: 0.8025, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6252/10000, Train Loss: 1.1201, Train Accuracy: 0.7958, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6253/10000, Train Loss: 1.1164, Train Accuracy: 0.7902, Val Loss: 1.1973, Val Accuracy: 0.7098 Epoch 6254/10000, Train Loss: 1.1062, Train Accuracy: 0.8092, Val Loss: 1.1973, Val Accuracy: 0.7143 Epoch 6255/10000, Train Loss: 1.1180, Train Accuracy: 0.7958, Val Loss: 1.1974, Val Accuracy: 0.7143 Epoch 6256/10000, Train Loss: 1.1143, Train Accuracy: 0.8036, Val Loss: 1.1977, Val Accuracy: 0.7098 Epoch 6257/10000, Train Loss: 1.1075, Train Accuracy: 0.8080, Val Loss: 1.1979, Val Accuracy: 0.7098 Epoch 6258/10000, Train Loss: 1.1125, Train Accuracy: 0.8013, Val Loss: 1.1976, Val Accuracy: 0.7098 Epoch 6259/10000, Train Loss: 1.1041, Train Accuracy: 0.8170, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6260/10000, Train Loss: 1.1069, Train Accuracy: 0.8114, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6261/10000, Train Loss: 1.1040, Train Accuracy: 0.8125, Val Loss: 1.1976, Val Accuracy: 0.7143 Epoch 6262/10000, Train Loss: 1.1170, Train Accuracy: 0.7946, Val Loss: 1.1978, Val Accuracy: 0.7143 Epoch 6263/10000, Train Loss: 1.1072, Train Accuracy: 0.8047, Val Loss: 1.1976, Val Accuracy: 0.7098 Epoch 6264/10000, Train Loss: 1.1123, Train Accuracy: 0.8013, Val Loss: 1.1976, Val Accuracy: 0.7098 Epoch 6265/10000, Train Loss: 1.1059, Train Accuracy: 0.8047, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6266/10000, Train Loss: 1.1061, Train Accuracy: 0.8069, Val Loss: 1.1976, Val Accuracy: 0.7098 Epoch 6267/10000, Train Loss: 1.1031, Train Accuracy: 0.8058, Val Loss: 1.1977, Val Accuracy: 0.7098 Epoch 6268/10000, Train Loss: 1.1139, Train Accuracy: 0.8002, Val Loss: 1.1977, Val Accuracy: 0.7143 Epoch 6269/10000, Train Loss: 1.1252, Train Accuracy: 0.7935, Val Loss: 1.1976, Val Accuracy: 0.7143 Epoch 6270/10000, Train Loss: 1.1082, Train Accuracy: 0.8103, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6271/10000, Train Loss: 1.1134, Train Accuracy: 0.7980, Val Loss: 1.1972, Val Accuracy: 0.7143 Epoch 6272/10000, Train Loss: 1.0998, Train Accuracy: 0.8181, Val Loss: 1.1972, Val Accuracy: 0.7098 Epoch 6273/10000, Train Loss: 1.1190, Train Accuracy: 0.7958, Val Loss: 1.1974, Val Accuracy: 0.7143 Epoch 6274/10000, Train Loss: 1.0974, Train Accuracy: 0.8203, Val Loss: 1.1972, Val Accuracy: 0.7143 Epoch 6275/10000, Train Loss: 1.1193, Train Accuracy: 0.7879, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6276/10000, Train Loss: 1.1146, Train Accuracy: 0.7958, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6277/10000, Train Loss: 1.1100, Train Accuracy: 0.8080, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6278/10000, Train Loss: 1.1148, Train Accuracy: 0.7958, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6279/10000, Train Loss: 1.1135, Train Accuracy: 0.7935, Val Loss: 1.1974, Val Accuracy: 0.7143 Epoch 6280/10000, Train Loss: 1.1181, Train Accuracy: 0.7980, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6281/10000, Train Loss: 1.1106, Train Accuracy: 0.8025, Val Loss: 1.1972, Val Accuracy: 0.7098 Epoch 6282/10000, Train Loss: 1.1035, Train Accuracy: 0.8080, Val Loss: 1.1972, Val Accuracy: 0.7098 Epoch 6283/10000, Train Loss: 1.1072, Train Accuracy: 0.8069, Val Loss: 1.1974, Val Accuracy: 0.7098 Epoch 6284/10000, Train Loss: 1.1192, Train Accuracy: 0.7958, Val Loss: 1.1975, Val Accuracy: 0.7098 Epoch 6285/10000, Train Loss: 1.1056, Train Accuracy: 0.8147, Val Loss: 1.1975, Val Accuracy: 0.7143 Epoch 6286/10000, Train Loss: 1.1189, Train Accuracy: 0.7891, Val Loss: 1.1976, Val Accuracy: 0.7143 Epoch 6287/10000, Train Loss: 1.1224, Train Accuracy: 0.7913, Val Loss: 1.1976, Val Accuracy: 0.7098 Epoch 6288/10000, Train Loss: 1.1096, Train Accuracy: 0.8058, Val Loss: 1.1974, Val Accuracy: 0.7188 Epoch 6289/10000, Train Loss: 1.1283, Train Accuracy: 0.7824, Val Loss: 1.1973, Val Accuracy: 0.7188 Epoch 6290/10000, Train Loss: 1.1136, Train Accuracy: 0.7980, Val Loss: 1.1972, Val Accuracy: 0.7143 Epoch 6291/10000, Train Loss: 1.1171, Train Accuracy: 0.7969, Val Loss: 1.1968, Val Accuracy: 0.7143 Epoch 6292/10000, Train Loss: 1.1052, Train Accuracy: 0.8069, Val Loss: 1.1965, Val Accuracy: 0.7143 Epoch 6293/10000, Train Loss: 1.1175, Train Accuracy: 0.8002, Val Loss: 1.1966, Val Accuracy: 0.7188 Epoch 6294/10000, Train Loss: 1.1128, Train Accuracy: 0.7980, Val Loss: 1.1964, Val Accuracy: 0.7188 Epoch 6295/10000, Train Loss: 1.1062, Train Accuracy: 0.8103, Val Loss: 1.1960, Val Accuracy: 0.7188 Epoch 6296/10000, Train Loss: 1.1089, Train Accuracy: 0.7980, Val Loss: 1.1959, Val Accuracy: 0.7143 Epoch 6297/10000, Train Loss: 1.1165, Train Accuracy: 0.7991, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6298/10000, Train Loss: 1.1069, Train Accuracy: 0.8114, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6299/10000, Train Loss: 1.0977, Train Accuracy: 0.8181, Val Loss: 1.1957, Val Accuracy: 0.7143 Epoch 6300/10000, Train Loss: 1.1077, Train Accuracy: 0.8047, Val Loss: 1.1957, Val Accuracy: 0.7232 Epoch 6301/10000, Train Loss: 1.1053, Train Accuracy: 0.8058, Val Loss: 1.1955, Val Accuracy: 0.7232 Epoch 6302/10000, Train Loss: 1.1094, Train Accuracy: 0.8013, Val Loss: 1.1952, Val Accuracy: 0.7188 Epoch 6303/10000, Train Loss: 1.1164, Train Accuracy: 0.8002, Val Loss: 1.1952, Val Accuracy: 0.7143 Epoch 6304/10000, Train Loss: 1.1102, Train Accuracy: 0.8069, Val Loss: 1.1949, Val Accuracy: 0.7188 Epoch 6305/10000, Train Loss: 1.1086, Train Accuracy: 0.8092, Val Loss: 1.1950, Val Accuracy: 0.7188 Epoch 6306/10000, Train Loss: 1.1058, Train Accuracy: 0.8147, Val Loss: 1.1947, Val Accuracy: 0.7188 Epoch 6307/10000, Train Loss: 1.1015, Train Accuracy: 0.8136, Val Loss: 1.1947, Val Accuracy: 0.7188 Epoch 6308/10000, Train Loss: 1.1134, Train Accuracy: 0.8002, Val Loss: 1.1947, Val Accuracy: 0.7188 Epoch 6309/10000, Train Loss: 1.1158, Train Accuracy: 0.7991, Val Loss: 1.1948, Val Accuracy: 0.7188 Epoch 6310/10000, Train Loss: 1.1122, Train Accuracy: 0.7946, Val Loss: 1.1950, Val Accuracy: 0.7232 Epoch 6311/10000, Train Loss: 1.1051, Train Accuracy: 0.8136, Val Loss: 1.1950, Val Accuracy: 0.7232 Epoch 6312/10000, Train Loss: 1.1077, Train Accuracy: 0.8069, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6313/10000, Train Loss: 1.1127, Train Accuracy: 0.8036, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6314/10000, Train Loss: 1.1160, Train Accuracy: 0.7991, Val Loss: 1.1958, Val Accuracy: 0.7232 Epoch 6315/10000, Train Loss: 1.1064, Train Accuracy: 0.8047, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6316/10000, Train Loss: 1.1075, Train Accuracy: 0.8125, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6317/10000, Train Loss: 1.1144, Train Accuracy: 0.8080, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6318/10000, Train Loss: 1.1130, Train Accuracy: 0.8058, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6319/10000, Train Loss: 1.1118, Train Accuracy: 0.8025, Val Loss: 1.1955, Val Accuracy: 0.7143 Epoch 6320/10000, Train Loss: 1.1127, Train Accuracy: 0.7924, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6321/10000, Train Loss: 1.1193, Train Accuracy: 0.7991, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6322/10000, Train Loss: 1.1116, Train Accuracy: 0.8002, Val Loss: 1.1951, Val Accuracy: 0.7232 Epoch 6323/10000, Train Loss: 1.1006, Train Accuracy: 0.8203, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6324/10000, Train Loss: 1.1149, Train Accuracy: 0.8002, Val Loss: 1.1952, Val Accuracy: 0.7232 Epoch 6325/10000, Train Loss: 1.1107, Train Accuracy: 0.8080, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6326/10000, Train Loss: 1.1172, Train Accuracy: 0.8036, Val Loss: 1.1952, Val Accuracy: 0.7188 Epoch 6327/10000, Train Loss: 1.1059, Train Accuracy: 0.8092, Val Loss: 1.1954, Val Accuracy: 0.7232 Epoch 6328/10000, Train Loss: 1.1221, Train Accuracy: 0.7857, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6329/10000, Train Loss: 1.1162, Train Accuracy: 0.7946, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6330/10000, Train Loss: 1.1123, Train Accuracy: 0.8147, Val Loss: 1.1953, Val Accuracy: 0.7188 Epoch 6331/10000, Train Loss: 1.0992, Train Accuracy: 0.8248, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6332/10000, Train Loss: 1.1024, Train Accuracy: 0.8147, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6333/10000, Train Loss: 1.1081, Train Accuracy: 0.8025, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6334/10000, Train Loss: 1.0941, Train Accuracy: 0.8147, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6335/10000, Train Loss: 1.1051, Train Accuracy: 0.8080, Val Loss: 1.1954, Val Accuracy: 0.7232 Epoch 6336/10000, Train Loss: 1.1167, Train Accuracy: 0.7868, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6337/10000, Train Loss: 1.1065, Train Accuracy: 0.8114, Val Loss: 1.1952, Val Accuracy: 0.7188 Epoch 6338/10000, Train Loss: 1.1144, Train Accuracy: 0.7980, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6339/10000, Train Loss: 1.1090, Train Accuracy: 0.8036, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6340/10000, Train Loss: 1.1078, Train Accuracy: 0.8047, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6341/10000, Train Loss: 1.1133, Train Accuracy: 0.8058, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6342/10000, Train Loss: 1.1058, Train Accuracy: 0.8047, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6343/10000, Train Loss: 1.1005, Train Accuracy: 0.8181, Val Loss: 1.1956, Val Accuracy: 0.7143 Epoch 6344/10000, Train Loss: 1.1119, Train Accuracy: 0.8103, Val Loss: 1.1957, Val Accuracy: 0.7143 Epoch 6345/10000, Train Loss: 1.1061, Train Accuracy: 0.8103, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6346/10000, Train Loss: 1.1134, Train Accuracy: 0.7946, Val Loss: 1.1959, Val Accuracy: 0.7188 Epoch 6347/10000, Train Loss: 1.1041, Train Accuracy: 0.8080, Val Loss: 1.1957, Val Accuracy: 0.7143 Epoch 6348/10000, Train Loss: 1.0967, Train Accuracy: 0.8214, Val Loss: 1.1956, Val Accuracy: 0.7143 Epoch 6349/10000, Train Loss: 1.1089, Train Accuracy: 0.8080, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6350/10000, Train Loss: 1.1053, Train Accuracy: 0.8125, Val Loss: 1.1957, Val Accuracy: 0.7143 Epoch 6351/10000, Train Loss: 1.1008, Train Accuracy: 0.8147, Val Loss: 1.1957, Val Accuracy: 0.7143 Epoch 6352/10000, Train Loss: 1.1160, Train Accuracy: 0.7958, Val Loss: 1.1954, Val Accuracy: 0.7143 Epoch 6353/10000, Train Loss: 1.1154, Train Accuracy: 0.7946, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6354/10000, Train Loss: 1.0999, Train Accuracy: 0.8158, Val Loss: 1.1960, Val Accuracy: 0.7143 Epoch 6355/10000, Train Loss: 1.1121, Train Accuracy: 0.8025, Val Loss: 1.1959, Val Accuracy: 0.7188 Epoch 6356/10000, Train Loss: 1.1005, Train Accuracy: 0.8158, Val Loss: 1.1959, Val Accuracy: 0.7143 Epoch 6357/10000, Train Loss: 1.0948, Train Accuracy: 0.8181, Val Loss: 1.1959, Val Accuracy: 0.7143 Epoch 6358/10000, Train Loss: 1.1238, Train Accuracy: 0.7868, Val Loss: 1.1959, Val Accuracy: 0.7143 Epoch 6359/10000, Train Loss: 1.1113, Train Accuracy: 0.8080, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6360/10000, Train Loss: 1.1036, Train Accuracy: 0.8058, Val Loss: 1.1956, Val Accuracy: 0.7143 Epoch 6361/10000, Train Loss: 1.1013, Train Accuracy: 0.8147, Val Loss: 1.1955, Val Accuracy: 0.7143 Epoch 6362/10000, Train Loss: 1.1150, Train Accuracy: 0.7991, Val Loss: 1.1954, Val Accuracy: 0.7143 Epoch 6363/10000, Train Loss: 1.1065, Train Accuracy: 0.8103, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6364/10000, Train Loss: 1.1081, Train Accuracy: 0.8103, Val Loss: 1.1953, Val Accuracy: 0.7188 Epoch 6365/10000, Train Loss: 1.1203, Train Accuracy: 0.7902, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6366/10000, Train Loss: 1.1064, Train Accuracy: 0.8069, Val Loss: 1.1954, Val Accuracy: 0.7143 Epoch 6367/10000, Train Loss: 1.1001, Train Accuracy: 0.8147, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6368/10000, Train Loss: 1.1108, Train Accuracy: 0.8002, Val Loss: 1.1955, Val Accuracy: 0.7143 Epoch 6369/10000, Train Loss: 1.0957, Train Accuracy: 0.8270, Val Loss: 1.1955, Val Accuracy: 0.7143 Epoch 6370/10000, Train Loss: 1.1100, Train Accuracy: 0.8025, Val Loss: 1.1952, Val Accuracy: 0.7098 Epoch 6371/10000, Train Loss: 1.1068, Train Accuracy: 0.8025, Val Loss: 1.1952, Val Accuracy: 0.7143 Epoch 6372/10000, Train Loss: 1.1103, Train Accuracy: 0.7924, Val Loss: 1.1956, Val Accuracy: 0.7098 Epoch 6373/10000, Train Loss: 1.1081, Train Accuracy: 0.8069, Val Loss: 1.1959, Val Accuracy: 0.7143 Epoch 6374/10000, Train Loss: 1.1035, Train Accuracy: 0.8080, Val Loss: 1.1957, Val Accuracy: 0.7143 Epoch 6375/10000, Train Loss: 1.1093, Train Accuracy: 0.8025, Val Loss: 1.1960, Val Accuracy: 0.7143 Epoch 6376/10000, Train Loss: 1.1099, Train Accuracy: 0.8058, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6377/10000, Train Loss: 1.1004, Train Accuracy: 0.8170, Val Loss: 1.1960, Val Accuracy: 0.7143 Epoch 6378/10000, Train Loss: 1.1116, Train Accuracy: 0.7946, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6379/10000, Train Loss: 1.1014, Train Accuracy: 0.8136, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6380/10000, Train Loss: 1.1083, Train Accuracy: 0.8080, Val Loss: 1.1958, Val Accuracy: 0.7232 Epoch 6381/10000, Train Loss: 1.1125, Train Accuracy: 0.8025, Val Loss: 1.1955, Val Accuracy: 0.7232 Epoch 6382/10000, Train Loss: 1.1145, Train Accuracy: 0.8025, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6383/10000, Train Loss: 1.1093, Train Accuracy: 0.7980, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6384/10000, Train Loss: 1.1002, Train Accuracy: 0.8125, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6385/10000, Train Loss: 1.1132, Train Accuracy: 0.8047, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6386/10000, Train Loss: 1.1045, Train Accuracy: 0.8158, Val Loss: 1.1955, Val Accuracy: 0.7143 Epoch 6387/10000, Train Loss: 1.0877, Train Accuracy: 0.8326, Val Loss: 1.1955, Val Accuracy: 0.7232 Epoch 6388/10000, Train Loss: 1.1177, Train Accuracy: 0.7980, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6389/10000, Train Loss: 1.1047, Train Accuracy: 0.8103, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6390/10000, Train Loss: 1.1061, Train Accuracy: 0.8013, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6391/10000, Train Loss: 1.0969, Train Accuracy: 0.8158, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6392/10000, Train Loss: 1.0959, Train Accuracy: 0.8136, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6393/10000, Train Loss: 1.1036, Train Accuracy: 0.8125, Val Loss: 1.1955, Val Accuracy: 0.7188 Epoch 6394/10000, Train Loss: 1.1065, Train Accuracy: 0.8025, Val Loss: 1.1958, Val Accuracy: 0.7188 Epoch 6395/10000, Train Loss: 1.0924, Train Accuracy: 0.8270, Val Loss: 1.1959, Val Accuracy: 0.7188 Epoch 6396/10000, Train Loss: 1.1056, Train Accuracy: 0.8203, Val Loss: 1.1960, Val Accuracy: 0.7232 Epoch 6397/10000, Train Loss: 1.1052, Train Accuracy: 0.8058, Val Loss: 1.1959, Val Accuracy: 0.7232 Epoch 6398/10000, Train Loss: 1.0989, Train Accuracy: 0.8136, Val Loss: 1.1958, Val Accuracy: 0.7277 Epoch 6399/10000, Train Loss: 1.1012, Train Accuracy: 0.8092, Val Loss: 1.1954, Val Accuracy: 0.7277 Epoch 6400/10000, Train Loss: 1.0886, Train Accuracy: 0.8326, Val Loss: 1.1957, Val Accuracy: 0.7232 Epoch 6401/10000, Train Loss: 1.1094, Train Accuracy: 0.8080, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6402/10000, Train Loss: 1.1093, Train Accuracy: 0.8025, Val Loss: 1.1957, Val Accuracy: 0.7188 Epoch 6403/10000, Train Loss: 1.0947, Train Accuracy: 0.8237, Val Loss: 1.1958, Val Accuracy: 0.7232 Epoch 6404/10000, Train Loss: 1.1113, Train Accuracy: 0.8114, Val Loss: 1.1953, Val Accuracy: 0.7232 Epoch 6405/10000, Train Loss: 1.0933, Train Accuracy: 0.8225, Val Loss: 1.1954, Val Accuracy: 0.7232 Epoch 6406/10000, Train Loss: 1.1064, Train Accuracy: 0.8080, Val Loss: 1.1952, Val Accuracy: 0.7232 Epoch 6407/10000, Train Loss: 1.1007, Train Accuracy: 0.8203, Val Loss: 1.1952, Val Accuracy: 0.7232 Epoch 6408/10000, Train Loss: 1.1036, Train Accuracy: 0.8058, Val Loss: 1.1951, Val Accuracy: 0.7232 Epoch 6409/10000, Train Loss: 1.1050, Train Accuracy: 0.8092, Val Loss: 1.1949, Val Accuracy: 0.7232 Epoch 6410/10000, Train Loss: 1.1087, Train Accuracy: 0.8058, Val Loss: 1.1950, Val Accuracy: 0.7232 Epoch 6411/10000, Train Loss: 1.0949, Train Accuracy: 0.8192, Val Loss: 1.1951, Val Accuracy: 0.7232 Epoch 6412/10000, Train Loss: 1.1131, Train Accuracy: 0.8002, Val Loss: 1.1950, Val Accuracy: 0.7232 Epoch 6413/10000, Train Loss: 1.1034, Train Accuracy: 0.8114, Val Loss: 1.1948, Val Accuracy: 0.7277 Epoch 6414/10000, Train Loss: 1.1097, Train Accuracy: 0.8025, Val Loss: 1.1951, Val Accuracy: 0.7277 Epoch 6415/10000, Train Loss: 1.1117, Train Accuracy: 0.8025, Val Loss: 1.1950, Val Accuracy: 0.7232 Epoch 6416/10000, Train Loss: 1.1031, Train Accuracy: 0.8092, Val Loss: 1.1952, Val Accuracy: 0.7232 Epoch 6417/10000, Train Loss: 1.0977, Train Accuracy: 0.8170, Val Loss: 1.1954, Val Accuracy: 0.7232 Epoch 6418/10000, Train Loss: 1.1156, Train Accuracy: 0.7902, Val Loss: 1.1955, Val Accuracy: 0.7277 Epoch 6419/10000, Train Loss: 1.1093, Train Accuracy: 0.8013, Val Loss: 1.1957, Val Accuracy: 0.7277 Epoch 6420/10000, Train Loss: 1.1010, Train Accuracy: 0.8125, Val Loss: 1.1957, Val Accuracy: 0.7277 Epoch 6421/10000, Train Loss: 1.1118, Train Accuracy: 0.7958, Val Loss: 1.1957, Val Accuracy: 0.7277 Epoch 6422/10000, Train Loss: 1.1115, Train Accuracy: 0.7935, Val Loss: 1.1958, Val Accuracy: 0.7143 Epoch 6423/10000, Train Loss: 1.1065, Train Accuracy: 0.7980, Val Loss: 1.1956, Val Accuracy: 0.7232 Epoch 6424/10000, Train Loss: 1.1088, Train Accuracy: 0.7980, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6425/10000, Train Loss: 1.0900, Train Accuracy: 0.8304, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6426/10000, Train Loss: 1.0977, Train Accuracy: 0.8181, Val Loss: 1.1956, Val Accuracy: 0.7188 Epoch 6427/10000, Train Loss: 1.1080, Train Accuracy: 0.8047, Val Loss: 1.1954, Val Accuracy: 0.7188 Epoch 6428/10000, Train Loss: 1.1136, Train Accuracy: 0.7991, Val Loss: 1.1949, Val Accuracy: 0.7098 Epoch 6429/10000, Train Loss: 1.1027, Train Accuracy: 0.8181, Val Loss: 1.1946, Val Accuracy: 0.7188 Epoch 6430/10000, Train Loss: 1.1018, Train Accuracy: 0.8147, Val Loss: 1.1946, Val Accuracy: 0.7143 Epoch 6431/10000, Train Loss: 1.0995, Train Accuracy: 0.8147, Val Loss: 1.1947, Val Accuracy: 0.7143 Epoch 6432/10000, Train Loss: 1.1088, Train Accuracy: 0.8069, Val Loss: 1.1945, Val Accuracy: 0.7188 Epoch 6433/10000, Train Loss: 1.0945, Train Accuracy: 0.8237, Val Loss: 1.1945, Val Accuracy: 0.7277 Epoch 6434/10000, Train Loss: 1.1027, Train Accuracy: 0.8136, Val Loss: 1.1946, Val Accuracy: 0.7232 Epoch 6435/10000, Train Loss: 1.0888, Train Accuracy: 0.8337, Val Loss: 1.1944, Val Accuracy: 0.7277 Epoch 6436/10000, Train Loss: 1.0995, Train Accuracy: 0.8147, Val Loss: 1.1943, Val Accuracy: 0.7232 Epoch 6437/10000, Train Loss: 1.1058, Train Accuracy: 0.8036, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6438/10000, Train Loss: 1.1166, Train Accuracy: 0.7969, Val Loss: 1.1940, Val Accuracy: 0.7277 Epoch 6439/10000, Train Loss: 1.1044, Train Accuracy: 0.8125, Val Loss: 1.1942, Val Accuracy: 0.7232 Epoch 6440/10000, Train Loss: 1.1127, Train Accuracy: 0.7991, Val Loss: 1.1942, Val Accuracy: 0.7277 Epoch 6441/10000, Train Loss: 1.0974, Train Accuracy: 0.8170, Val Loss: 1.1942, Val Accuracy: 0.7232 Epoch 6442/10000, Train Loss: 1.1153, Train Accuracy: 0.7991, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6443/10000, Train Loss: 1.1019, Train Accuracy: 0.8114, Val Loss: 1.1944, Val Accuracy: 0.7232 Epoch 6444/10000, Train Loss: 1.1105, Train Accuracy: 0.8103, Val Loss: 1.1946, Val Accuracy: 0.7232 Epoch 6445/10000, Train Loss: 1.0960, Train Accuracy: 0.8147, Val Loss: 1.1949, Val Accuracy: 0.7232 Epoch 6446/10000, Train Loss: 1.1026, Train Accuracy: 0.8103, Val Loss: 1.1948, Val Accuracy: 0.7232 Epoch 6447/10000, Train Loss: 1.1074, Train Accuracy: 0.8047, Val Loss: 1.1944, Val Accuracy: 0.7232 Epoch 6448/10000, Train Loss: 1.1146, Train Accuracy: 0.7991, Val Loss: 1.1942, Val Accuracy: 0.7232 Epoch 6449/10000, Train Loss: 1.1061, Train Accuracy: 0.8114, Val Loss: 1.1942, Val Accuracy: 0.7188 Epoch 6450/10000, Train Loss: 1.1117, Train Accuracy: 0.8036, Val Loss: 1.1939, Val Accuracy: 0.7232 Epoch 6451/10000, Train Loss: 1.1089, Train Accuracy: 0.7980, Val Loss: 1.1940, Val Accuracy: 0.7277 Epoch 6452/10000, Train Loss: 1.0965, Train Accuracy: 0.8214, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6453/10000, Train Loss: 1.1144, Train Accuracy: 0.7868, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6454/10000, Train Loss: 1.0932, Train Accuracy: 0.8170, Val Loss: 1.1937, Val Accuracy: 0.7232 Epoch 6455/10000, Train Loss: 1.1067, Train Accuracy: 0.8103, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6456/10000, Train Loss: 1.1066, Train Accuracy: 0.8047, Val Loss: 1.1940, Val Accuracy: 0.7232 Epoch 6457/10000, Train Loss: 1.0962, Train Accuracy: 0.8147, Val Loss: 1.1938, Val Accuracy: 0.7321 Epoch 6458/10000, Train Loss: 1.1083, Train Accuracy: 0.8092, Val Loss: 1.1938, Val Accuracy: 0.7321 Epoch 6459/10000, Train Loss: 1.1183, Train Accuracy: 0.7958, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6460/10000, Train Loss: 1.1071, Train Accuracy: 0.8125, Val Loss: 1.1939, Val Accuracy: 0.7277 Epoch 6461/10000, Train Loss: 1.1007, Train Accuracy: 0.8225, Val Loss: 1.1940, Val Accuracy: 0.7277 Epoch 6462/10000, Train Loss: 1.1000, Train Accuracy: 0.8170, Val Loss: 1.1943, Val Accuracy: 0.7277 Epoch 6463/10000, Train Loss: 1.0940, Train Accuracy: 0.8147, Val Loss: 1.1941, Val Accuracy: 0.7232 Epoch 6464/10000, Train Loss: 1.0981, Train Accuracy: 0.8136, Val Loss: 1.1939, Val Accuracy: 0.7277 Epoch 6465/10000, Train Loss: 1.1009, Train Accuracy: 0.8147, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6466/10000, Train Loss: 1.0970, Train Accuracy: 0.8237, Val Loss: 1.1941, Val Accuracy: 0.7232 Epoch 6467/10000, Train Loss: 1.1121, Train Accuracy: 0.7991, Val Loss: 1.1943, Val Accuracy: 0.7277 Epoch 6468/10000, Train Loss: 1.1007, Train Accuracy: 0.8158, Val Loss: 1.1940, Val Accuracy: 0.7321 Epoch 6469/10000, Train Loss: 1.1034, Train Accuracy: 0.8058, Val Loss: 1.1942, Val Accuracy: 0.7277 Epoch 6470/10000, Train Loss: 1.0915, Train Accuracy: 0.8192, Val Loss: 1.1942, Val Accuracy: 0.7232 Epoch 6471/10000, Train Loss: 1.0946, Train Accuracy: 0.8158, Val Loss: 1.1942, Val Accuracy: 0.7277 Epoch 6472/10000, Train Loss: 1.1093, Train Accuracy: 0.8080, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6473/10000, Train Loss: 1.0828, Train Accuracy: 0.8337, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6474/10000, Train Loss: 1.1150, Train Accuracy: 0.8013, Val Loss: 1.1941, Val Accuracy: 0.7321 Epoch 6475/10000, Train Loss: 1.0982, Train Accuracy: 0.8136, Val Loss: 1.1938, Val Accuracy: 0.7277 Epoch 6476/10000, Train Loss: 1.1050, Train Accuracy: 0.8170, Val Loss: 1.1940, Val Accuracy: 0.7277 Epoch 6477/10000, Train Loss: 1.1019, Train Accuracy: 0.8103, Val Loss: 1.1933, Val Accuracy: 0.7277 Epoch 6478/10000, Train Loss: 1.1069, Train Accuracy: 0.8069, Val Loss: 1.1934, Val Accuracy: 0.7321 Epoch 6479/10000, Train Loss: 1.0999, Train Accuracy: 0.8203, Val Loss: 1.1936, Val Accuracy: 0.7232 Epoch 6480/10000, Train Loss: 1.1080, Train Accuracy: 0.7958, Val Loss: 1.1937, Val Accuracy: 0.7232 Epoch 6481/10000, Train Loss: 1.1165, Train Accuracy: 0.7958, Val Loss: 1.1934, Val Accuracy: 0.7188 Epoch 6482/10000, Train Loss: 1.1039, Train Accuracy: 0.8114, Val Loss: 1.1936, Val Accuracy: 0.7232 Epoch 6483/10000, Train Loss: 1.1118, Train Accuracy: 0.7991, Val Loss: 1.1934, Val Accuracy: 0.7232 Epoch 6484/10000, Train Loss: 1.0852, Train Accuracy: 0.8393, Val Loss: 1.1932, Val Accuracy: 0.7232 Epoch 6485/10000, Train Loss: 1.1053, Train Accuracy: 0.8058, Val Loss: 1.1936, Val Accuracy: 0.7232 Epoch 6486/10000, Train Loss: 1.1012, Train Accuracy: 0.8147, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6487/10000, Train Loss: 1.1078, Train Accuracy: 0.8080, Val Loss: 1.1938, Val Accuracy: 0.7232 Epoch 6488/10000, Train Loss: 1.0961, Train Accuracy: 0.8203, Val Loss: 1.1939, Val Accuracy: 0.7232 Epoch 6489/10000, Train Loss: 1.1019, Train Accuracy: 0.8125, Val Loss: 1.1937, Val Accuracy: 0.7232 Epoch 6490/10000, Train Loss: 1.1085, Train Accuracy: 0.8158, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6491/10000, Train Loss: 1.1070, Train Accuracy: 0.8069, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6492/10000, Train Loss: 1.0984, Train Accuracy: 0.8192, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6493/10000, Train Loss: 1.1000, Train Accuracy: 0.8170, Val Loss: 1.1938, Val Accuracy: 0.7232 Epoch 6494/10000, Train Loss: 1.1187, Train Accuracy: 0.7902, Val Loss: 1.1940, Val Accuracy: 0.7188 Epoch 6495/10000, Train Loss: 1.0961, Train Accuracy: 0.8170, Val Loss: 1.1942, Val Accuracy: 0.7232 Epoch 6496/10000, Train Loss: 1.0994, Train Accuracy: 0.8125, Val Loss: 1.1942, Val Accuracy: 0.7232 Epoch 6497/10000, Train Loss: 1.1019, Train Accuracy: 0.8136, Val Loss: 1.1943, Val Accuracy: 0.7232 Epoch 6498/10000, Train Loss: 1.1062, Train Accuracy: 0.8103, Val Loss: 1.1943, Val Accuracy: 0.7188 Epoch 6499/10000, Train Loss: 1.0991, Train Accuracy: 0.8047, Val Loss: 1.1941, Val Accuracy: 0.7188 Epoch 6500/10000, Train Loss: 1.1008, Train Accuracy: 0.8136, Val Loss: 1.1940, Val Accuracy: 0.7232 Epoch 6501/10000, Train Loss: 1.1154, Train Accuracy: 0.7991, Val Loss: 1.1940, Val Accuracy: 0.7232 Epoch 6502/10000, Train Loss: 1.1020, Train Accuracy: 0.8147, Val Loss: 1.1940, Val Accuracy: 0.7277 Epoch 6503/10000, Train Loss: 1.0848, Train Accuracy: 0.8348, Val Loss: 1.1938, Val Accuracy: 0.7277 Epoch 6504/10000, Train Loss: 1.1078, Train Accuracy: 0.8069, Val Loss: 1.1938, Val Accuracy: 0.7277 Epoch 6505/10000, Train Loss: 1.1115, Train Accuracy: 0.8058, Val Loss: 1.1939, Val Accuracy: 0.7232 Epoch 6506/10000, Train Loss: 1.1025, Train Accuracy: 0.8147, Val Loss: 1.1941, Val Accuracy: 0.7277 Epoch 6507/10000, Train Loss: 1.1114, Train Accuracy: 0.8002, Val Loss: 1.1942, Val Accuracy: 0.7188 Epoch 6508/10000, Train Loss: 1.1008, Train Accuracy: 0.8192, Val Loss: 1.1945, Val Accuracy: 0.7232 Epoch 6509/10000, Train Loss: 1.1184, Train Accuracy: 0.7958, Val Loss: 1.1942, Val Accuracy: 0.7277 Epoch 6510/10000, Train Loss: 1.1078, Train Accuracy: 0.8069, Val Loss: 1.1939, Val Accuracy: 0.7277 Epoch 6511/10000, Train Loss: 1.0978, Train Accuracy: 0.8136, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6512/10000, Train Loss: 1.1080, Train Accuracy: 0.8080, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6513/10000, Train Loss: 1.1095, Train Accuracy: 0.8069, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6514/10000, Train Loss: 1.0996, Train Accuracy: 0.8214, Val Loss: 1.1934, Val Accuracy: 0.7277 Epoch 6515/10000, Train Loss: 1.1059, Train Accuracy: 0.8114, Val Loss: 1.1938, Val Accuracy: 0.7277 Epoch 6516/10000, Train Loss: 1.0964, Train Accuracy: 0.8203, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6517/10000, Train Loss: 1.0969, Train Accuracy: 0.8281, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6518/10000, Train Loss: 1.0946, Train Accuracy: 0.8170, Val Loss: 1.1937, Val Accuracy: 0.7277 Epoch 6519/10000, Train Loss: 1.1041, Train Accuracy: 0.8047, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6520/10000, Train Loss: 1.1087, Train Accuracy: 0.8036, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6521/10000, Train Loss: 1.0983, Train Accuracy: 0.8136, Val Loss: 1.1934, Val Accuracy: 0.7277 Epoch 6522/10000, Train Loss: 1.0890, Train Accuracy: 0.8281, Val Loss: 1.1932, Val Accuracy: 0.7277 Epoch 6523/10000, Train Loss: 1.1004, Train Accuracy: 0.8147, Val Loss: 1.1934, Val Accuracy: 0.7277 Epoch 6524/10000, Train Loss: 1.1115, Train Accuracy: 0.7969, Val Loss: 1.1934, Val Accuracy: 0.7277 Epoch 6525/10000, Train Loss: 1.1016, Train Accuracy: 0.8080, Val Loss: 1.1932, Val Accuracy: 0.7277 Epoch 6526/10000, Train Loss: 1.0928, Train Accuracy: 0.8203, Val Loss: 1.1930, Val Accuracy: 0.7277 Epoch 6527/10000, Train Loss: 1.1097, Train Accuracy: 0.7913, Val Loss: 1.1930, Val Accuracy: 0.7277 Epoch 6528/10000, Train Loss: 1.1190, Train Accuracy: 0.7969, Val Loss: 1.1932, Val Accuracy: 0.7277 Epoch 6529/10000, Train Loss: 1.1009, Train Accuracy: 0.8103, Val Loss: 1.1934, Val Accuracy: 0.7277 Epoch 6530/10000, Train Loss: 1.0920, Train Accuracy: 0.8259, Val Loss: 1.1932, Val Accuracy: 0.7277 Epoch 6531/10000, Train Loss: 1.1052, Train Accuracy: 0.8013, Val Loss: 1.1936, Val Accuracy: 0.7277 Epoch 6532/10000, Train Loss: 1.0986, Train Accuracy: 0.8147, Val Loss: 1.1936, Val Accuracy: 0.7232 Epoch 6533/10000, Train Loss: 1.1128, Train Accuracy: 0.7935, Val Loss: 1.1935, Val Accuracy: 0.7188 Epoch 6534/10000, Train Loss: 1.1018, Train Accuracy: 0.8225, Val Loss: 1.1935, Val Accuracy: 0.7188 Epoch 6535/10000, Train Loss: 1.1052, Train Accuracy: 0.8125, Val Loss: 1.1930, Val Accuracy: 0.7188 Epoch 6536/10000, Train Loss: 1.1076, Train Accuracy: 0.8092, Val Loss: 1.1929, Val Accuracy: 0.7232 Epoch 6537/10000, Train Loss: 1.1001, Train Accuracy: 0.8158, Val Loss: 1.1933, Val Accuracy: 0.7232 Epoch 6538/10000, Train Loss: 1.1098, Train Accuracy: 0.8036, Val Loss: 1.1930, Val Accuracy: 0.7188 Epoch 6539/10000, Train Loss: 1.1055, Train Accuracy: 0.8092, Val Loss: 1.1928, Val Accuracy: 0.7188 Epoch 6540/10000, Train Loss: 1.1078, Train Accuracy: 0.8002, Val Loss: 1.1927, Val Accuracy: 0.7188 Epoch 6541/10000, Train Loss: 1.0987, Train Accuracy: 0.8103, Val Loss: 1.1929, Val Accuracy: 0.7188 Epoch 6542/10000, Train Loss: 1.1052, Train Accuracy: 0.8114, Val Loss: 1.1927, Val Accuracy: 0.7143 Epoch 6543/10000, Train Loss: 1.1090, Train Accuracy: 0.8036, Val Loss: 1.1928, Val Accuracy: 0.7188 Epoch 6544/10000, Train Loss: 1.1088, Train Accuracy: 0.8025, Val Loss: 1.1931, Val Accuracy: 0.7188 Epoch 6545/10000, Train Loss: 1.1023, Train Accuracy: 0.8170, Val Loss: 1.1930, Val Accuracy: 0.7188 Epoch 6546/10000, Train Loss: 1.1013, Train Accuracy: 0.8181, Val Loss: 1.1931, Val Accuracy: 0.7188 Epoch 6547/10000, Train Loss: 1.1087, Train Accuracy: 0.8047, Val Loss: 1.1930, Val Accuracy: 0.7232 Epoch 6548/10000, Train Loss: 1.1064, Train Accuracy: 0.8080, Val Loss: 1.1929, Val Accuracy: 0.7232 Epoch 6549/10000, Train Loss: 1.1075, Train Accuracy: 0.8047, Val Loss: 1.1928, Val Accuracy: 0.7232 Epoch 6550/10000, Train Loss: 1.0870, Train Accuracy: 0.8292, Val Loss: 1.1926, Val Accuracy: 0.7232 Epoch 6551/10000, Train Loss: 1.1039, Train Accuracy: 0.8125, Val Loss: 1.1925, Val Accuracy: 0.7232 Epoch 6552/10000, Train Loss: 1.1050, Train Accuracy: 0.8103, Val Loss: 1.1924, Val Accuracy: 0.7232 Epoch 6553/10000, Train Loss: 1.1023, Train Accuracy: 0.8080, Val Loss: 1.1923, Val Accuracy: 0.7232 Epoch 6554/10000, Train Loss: 1.1076, Train Accuracy: 0.8025, Val Loss: 1.1922, Val Accuracy: 0.7188 Epoch 6555/10000, Train Loss: 1.1013, Train Accuracy: 0.8114, Val Loss: 1.1924, Val Accuracy: 0.7188 Epoch 6556/10000, Train Loss: 1.0991, Train Accuracy: 0.8136, Val Loss: 1.1924, Val Accuracy: 0.7188 Epoch 6557/10000, Train Loss: 1.1058, Train Accuracy: 0.8147, Val Loss: 1.1924, Val Accuracy: 0.7188 Epoch 6558/10000, Train Loss: 1.1033, Train Accuracy: 0.8036, Val Loss: 1.1923, Val Accuracy: 0.7188 Epoch 6559/10000, Train Loss: 1.1126, Train Accuracy: 0.7991, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6560/10000, Train Loss: 1.0995, Train Accuracy: 0.8214, Val Loss: 1.1920, Val Accuracy: 0.7143 Epoch 6561/10000, Train Loss: 1.0957, Train Accuracy: 0.8181, Val Loss: 1.1921, Val Accuracy: 0.7143 Epoch 6562/10000, Train Loss: 1.0972, Train Accuracy: 0.8147, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6563/10000, Train Loss: 1.1036, Train Accuracy: 0.8069, Val Loss: 1.1921, Val Accuracy: 0.7143 Epoch 6564/10000, Train Loss: 1.1069, Train Accuracy: 0.8069, Val Loss: 1.1923, Val Accuracy: 0.7188 Epoch 6565/10000, Train Loss: 1.0965, Train Accuracy: 0.8192, Val Loss: 1.1924, Val Accuracy: 0.7143 Epoch 6566/10000, Train Loss: 1.1030, Train Accuracy: 0.8092, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6567/10000, Train Loss: 1.0986, Train Accuracy: 0.8214, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6568/10000, Train Loss: 1.1050, Train Accuracy: 0.8069, Val Loss: 1.1929, Val Accuracy: 0.7143 Epoch 6569/10000, Train Loss: 1.1034, Train Accuracy: 0.8114, Val Loss: 1.1928, Val Accuracy: 0.7188 Epoch 6570/10000, Train Loss: 1.1066, Train Accuracy: 0.8114, Val Loss: 1.1927, Val Accuracy: 0.7143 Epoch 6571/10000, Train Loss: 1.0984, Train Accuracy: 0.8158, Val Loss: 1.1927, Val Accuracy: 0.7143 Epoch 6572/10000, Train Loss: 1.0919, Train Accuracy: 0.8237, Val Loss: 1.1926, Val Accuracy: 0.7188 Epoch 6573/10000, Train Loss: 1.0933, Train Accuracy: 0.8225, Val Loss: 1.1926, Val Accuracy: 0.7232 Epoch 6574/10000, Train Loss: 1.1076, Train Accuracy: 0.8092, Val Loss: 1.1927, Val Accuracy: 0.7188 Epoch 6575/10000, Train Loss: 1.1049, Train Accuracy: 0.8080, Val Loss: 1.1926, Val Accuracy: 0.7188 Epoch 6576/10000, Train Loss: 1.1045, Train Accuracy: 0.8147, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6577/10000, Train Loss: 1.1066, Train Accuracy: 0.8025, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6578/10000, Train Loss: 1.0942, Train Accuracy: 0.8214, Val Loss: 1.1924, Val Accuracy: 0.7143 Epoch 6579/10000, Train Loss: 1.1048, Train Accuracy: 0.8080, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6580/10000, Train Loss: 1.0987, Train Accuracy: 0.8259, Val Loss: 1.1928, Val Accuracy: 0.7143 Epoch 6581/10000, Train Loss: 1.1017, Train Accuracy: 0.8103, Val Loss: 1.1930, Val Accuracy: 0.7143 Epoch 6582/10000, Train Loss: 1.0960, Train Accuracy: 0.8203, Val Loss: 1.1929, Val Accuracy: 0.7143 Epoch 6583/10000, Train Loss: 1.0987, Train Accuracy: 0.8069, Val Loss: 1.1928, Val Accuracy: 0.7143 Epoch 6584/10000, Train Loss: 1.0911, Train Accuracy: 0.8237, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6585/10000, Train Loss: 1.1107, Train Accuracy: 0.8058, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6586/10000, Train Loss: 1.0995, Train Accuracy: 0.8080, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6587/10000, Train Loss: 1.1115, Train Accuracy: 0.7969, Val Loss: 1.1927, Val Accuracy: 0.7143 Epoch 6588/10000, Train Loss: 1.1043, Train Accuracy: 0.8092, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6589/10000, Train Loss: 1.0998, Train Accuracy: 0.8136, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6590/10000, Train Loss: 1.1082, Train Accuracy: 0.8025, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6591/10000, Train Loss: 1.0947, Train Accuracy: 0.8259, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6592/10000, Train Loss: 1.0948, Train Accuracy: 0.8214, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6593/10000, Train Loss: 1.1121, Train Accuracy: 0.8069, Val Loss: 1.1924, Val Accuracy: 0.7143 Epoch 6594/10000, Train Loss: 1.0997, Train Accuracy: 0.8170, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6595/10000, Train Loss: 1.0997, Train Accuracy: 0.8136, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6596/10000, Train Loss: 1.0991, Train Accuracy: 0.8092, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6597/10000, Train Loss: 1.0977, Train Accuracy: 0.8237, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6598/10000, Train Loss: 1.0980, Train Accuracy: 0.8136, Val Loss: 1.1926, Val Accuracy: 0.7143 Epoch 6599/10000, Train Loss: 1.1048, Train Accuracy: 0.8092, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6600/10000, Train Loss: 1.1011, Train Accuracy: 0.8080, Val Loss: 1.1924, Val Accuracy: 0.7143 Epoch 6601/10000, Train Loss: 1.1046, Train Accuracy: 0.8058, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6602/10000, Train Loss: 1.0939, Train Accuracy: 0.8170, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6603/10000, Train Loss: 1.1045, Train Accuracy: 0.7991, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6604/10000, Train Loss: 1.1007, Train Accuracy: 0.8136, Val Loss: 1.1920, Val Accuracy: 0.7143 Epoch 6605/10000, Train Loss: 1.0982, Train Accuracy: 0.8214, Val Loss: 1.1920, Val Accuracy: 0.7143 Epoch 6606/10000, Train Loss: 1.1038, Train Accuracy: 0.8103, Val Loss: 1.1923, Val Accuracy: 0.7143 Epoch 6607/10000, Train Loss: 1.0923, Train Accuracy: 0.8237, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6608/10000, Train Loss: 1.1068, Train Accuracy: 0.8025, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6609/10000, Train Loss: 1.0997, Train Accuracy: 0.8170, Val Loss: 1.1925, Val Accuracy: 0.7143 Epoch 6610/10000, Train Loss: 1.1046, Train Accuracy: 0.8103, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6611/10000, Train Loss: 1.0976, Train Accuracy: 0.8181, Val Loss: 1.1922, Val Accuracy: 0.7143 Epoch 6612/10000, Train Loss: 1.0884, Train Accuracy: 0.8281, Val Loss: 1.1923, Val Accuracy: 0.7188 Epoch 6613/10000, Train Loss: 1.0999, Train Accuracy: 0.8114, Val Loss: 1.1921, Val Accuracy: 0.7188 Epoch 6614/10000, Train Loss: 1.0987, Train Accuracy: 0.8103, Val Loss: 1.1917, Val Accuracy: 0.7143 Epoch 6615/10000, Train Loss: 1.1129, Train Accuracy: 0.8002, Val Loss: 1.1919, Val Accuracy: 0.7188 Epoch 6616/10000, Train Loss: 1.0975, Train Accuracy: 0.8170, Val Loss: 1.1919, Val Accuracy: 0.7188 Epoch 6617/10000, Train Loss: 1.1094, Train Accuracy: 0.8058, Val Loss: 1.1916, Val Accuracy: 0.7188 Epoch 6618/10000, Train Loss: 1.1058, Train Accuracy: 0.8103, Val Loss: 1.1917, Val Accuracy: 0.7188 Epoch 6619/10000, Train Loss: 1.1052, Train Accuracy: 0.8058, Val Loss: 1.1916, Val Accuracy: 0.7188 Epoch 6620/10000, Train Loss: 1.1027, Train Accuracy: 0.8080, Val Loss: 1.1914, Val Accuracy: 0.7188 Epoch 6621/10000, Train Loss: 1.0966, Train Accuracy: 0.8214, Val Loss: 1.1915, Val Accuracy: 0.7188 Epoch 6622/10000, Train Loss: 1.0969, Train Accuracy: 0.8181, Val Loss: 1.1914, Val Accuracy: 0.7188 Epoch 6623/10000, Train Loss: 1.0972, Train Accuracy: 0.8158, Val Loss: 1.1914, Val Accuracy: 0.7188 Epoch 6624/10000, Train Loss: 1.0926, Train Accuracy: 0.8248, Val Loss: 1.1915, Val Accuracy: 0.7188 Epoch 6625/10000, Train Loss: 1.0993, Train Accuracy: 0.8170, Val Loss: 1.1914, Val Accuracy: 0.7188 Epoch 6626/10000, Train Loss: 1.1017, Train Accuracy: 0.8125, Val Loss: 1.1915, Val Accuracy: 0.7188 Epoch 6627/10000, Train Loss: 1.1009, Train Accuracy: 0.8170, Val Loss: 1.1913, Val Accuracy: 0.7143 Epoch 6628/10000, Train Loss: 1.1012, Train Accuracy: 0.8103, Val Loss: 1.1914, Val Accuracy: 0.7143 Epoch 6629/10000, Train Loss: 1.0973, Train Accuracy: 0.8136, Val Loss: 1.1914, Val Accuracy: 0.7143 Epoch 6630/10000, Train Loss: 1.1001, Train Accuracy: 0.8092, Val Loss: 1.1914, Val Accuracy: 0.7188 Epoch 6631/10000, Train Loss: 1.0983, Train Accuracy: 0.8125, Val Loss: 1.1910, Val Accuracy: 0.7188 Epoch 6632/10000, Train Loss: 1.1096, Train Accuracy: 0.8002, Val Loss: 1.1913, Val Accuracy: 0.7188 Epoch 6633/10000, Train Loss: 1.0984, Train Accuracy: 0.8181, Val Loss: 1.1913, Val Accuracy: 0.7188 Epoch 6634/10000, Train Loss: 1.0939, Train Accuracy: 0.8170, Val Loss: 1.1914, Val Accuracy: 0.7188 Epoch 6635/10000, Train Loss: 1.1027, Train Accuracy: 0.8103, Val Loss: 1.1912, Val Accuracy: 0.7143 Epoch 6636/10000, Train Loss: 1.0938, Train Accuracy: 0.8259, Val Loss: 1.1911, Val Accuracy: 0.7188 Epoch 6637/10000, Train Loss: 1.0909, Train Accuracy: 0.8281, Val Loss: 1.1909, Val Accuracy: 0.7188 Epoch 6638/10000, Train Loss: 1.1106, Train Accuracy: 0.7980, Val Loss: 1.1910, Val Accuracy: 0.7188 Epoch 6639/10000, Train Loss: 1.1195, Train Accuracy: 0.7879, Val Loss: 1.1908, Val Accuracy: 0.7188 Epoch 6640/10000, Train Loss: 1.1011, Train Accuracy: 0.8114, Val Loss: 1.1909, Val Accuracy: 0.7188 Epoch 6641/10000, Train Loss: 1.1044, Train Accuracy: 0.8080, Val Loss: 1.1907, Val Accuracy: 0.7188 Epoch 6642/10000, Train Loss: 1.1167, Train Accuracy: 0.8002, Val Loss: 1.1905, Val Accuracy: 0.7188 Epoch 6643/10000, Train Loss: 1.0976, Train Accuracy: 0.8136, Val Loss: 1.1907, Val Accuracy: 0.7188 Epoch 6644/10000, Train Loss: 1.0929, Train Accuracy: 0.8192, Val Loss: 1.1905, Val Accuracy: 0.7188 Epoch 6645/10000, Train Loss: 1.0840, Train Accuracy: 0.8315, Val Loss: 1.1902, Val Accuracy: 0.7188 Epoch 6646/10000, Train Loss: 1.0959, Train Accuracy: 0.8214, Val Loss: 1.1903, Val Accuracy: 0.7188 Epoch 6647/10000, Train Loss: 1.1046, Train Accuracy: 0.8025, Val Loss: 1.1905, Val Accuracy: 0.7188 Epoch 6648/10000, Train Loss: 1.1026, Train Accuracy: 0.8192, Val Loss: 1.1906, Val Accuracy: 0.7188 Epoch 6649/10000, Train Loss: 1.0971, Train Accuracy: 0.8080, Val Loss: 1.1904, Val Accuracy: 0.7188 Epoch 6650/10000, Train Loss: 1.1098, Train Accuracy: 0.8025, Val Loss: 1.1904, Val Accuracy: 0.7188 Epoch 6651/10000, Train Loss: 1.0954, Train Accuracy: 0.8147, Val Loss: 1.1906, Val Accuracy: 0.7188 Epoch 6652/10000, Train Loss: 1.1056, Train Accuracy: 0.8058, Val Loss: 1.1906, Val Accuracy: 0.7188 Epoch 6653/10000, Train Loss: 1.0922, Train Accuracy: 0.8237, Val Loss: 1.1905, Val Accuracy: 0.7188 Epoch 6654/10000, Train Loss: 1.1017, Train Accuracy: 0.8170, Val Loss: 1.1902, Val Accuracy: 0.7188 Epoch 6655/10000, Train Loss: 1.0982, Train Accuracy: 0.8125, Val Loss: 1.1900, Val Accuracy: 0.7188 Epoch 6656/10000, Train Loss: 1.0844, Train Accuracy: 0.8281, Val Loss: 1.1904, Val Accuracy: 0.7188 Epoch 6657/10000, Train Loss: 1.1001, Train Accuracy: 0.8158, Val Loss: 1.1902, Val Accuracy: 0.7188 Epoch 6658/10000, Train Loss: 1.1027, Train Accuracy: 0.8080, Val Loss: 1.1901, Val Accuracy: 0.7188 Epoch 6659/10000, Train Loss: 1.1027, Train Accuracy: 0.8136, Val Loss: 1.1903, Val Accuracy: 0.7188 Epoch 6660/10000, Train Loss: 1.1140, Train Accuracy: 0.8025, Val Loss: 1.1904, Val Accuracy: 0.7188 Epoch 6661/10000, Train Loss: 1.1055, Train Accuracy: 0.8047, Val Loss: 1.1903, Val Accuracy: 0.7188 Epoch 6662/10000, Train Loss: 1.0936, Train Accuracy: 0.8214, Val Loss: 1.1903, Val Accuracy: 0.7188 Epoch 6663/10000, Train Loss: 1.0967, Train Accuracy: 0.8125, Val Loss: 1.1899, Val Accuracy: 0.7188 Epoch 6664/10000, Train Loss: 1.1016, Train Accuracy: 0.8103, Val Loss: 1.1899, Val Accuracy: 0.7188 Epoch 6665/10000, Train Loss: 1.0976, Train Accuracy: 0.8147, Val Loss: 1.1898, Val Accuracy: 0.7188 Epoch 6666/10000, Train Loss: 1.0909, Train Accuracy: 0.8237, Val Loss: 1.1899, Val Accuracy: 0.7188 Epoch 6667/10000, Train Loss: 1.0863, Train Accuracy: 0.8326, Val Loss: 1.1899, Val Accuracy: 0.7232 Epoch 6668/10000, Train Loss: 1.0990, Train Accuracy: 0.8158, Val Loss: 1.1899, Val Accuracy: 0.7188 Epoch 6669/10000, Train Loss: 1.1014, Train Accuracy: 0.8069, Val Loss: 1.1900, Val Accuracy: 0.7188 Epoch 6670/10000, Train Loss: 1.1023, Train Accuracy: 0.8092, Val Loss: 1.1902, Val Accuracy: 0.7188 Epoch 6671/10000, Train Loss: 1.0976, Train Accuracy: 0.8158, Val Loss: 1.1903, Val Accuracy: 0.7188 Epoch 6672/10000, Train Loss: 1.0933, Train Accuracy: 0.8214, Val Loss: 1.1904, Val Accuracy: 0.7188 Epoch 6673/10000, Train Loss: 1.1070, Train Accuracy: 0.8080, Val Loss: 1.1901, Val Accuracy: 0.7188 Epoch 6674/10000, Train Loss: 1.0922, Train Accuracy: 0.8181, Val Loss: 1.1900, Val Accuracy: 0.7188 Epoch 6675/10000, Train Loss: 1.1068, Train Accuracy: 0.8025, Val Loss: 1.1899, Val Accuracy: 0.7188 Epoch 6676/10000, Train Loss: 1.0949, Train Accuracy: 0.8147, Val Loss: 1.1897, Val Accuracy: 0.7188 Epoch 6677/10000, Train Loss: 1.1019, Train Accuracy: 0.8047, Val Loss: 1.1896, Val Accuracy: 0.7188 Epoch 6678/10000, Train Loss: 1.1087, Train Accuracy: 0.8025, Val Loss: 1.1895, Val Accuracy: 0.7188 Epoch 6679/10000, Train Loss: 1.0906, Train Accuracy: 0.8292, Val Loss: 1.1893, Val Accuracy: 0.7188 Epoch 6680/10000, Train Loss: 1.0987, Train Accuracy: 0.8158, Val Loss: 1.1888, Val Accuracy: 0.7188 Epoch 6681/10000, Train Loss: 1.1018, Train Accuracy: 0.8092, Val Loss: 1.1888, Val Accuracy: 0.7188 Epoch 6682/10000, Train Loss: 1.0993, Train Accuracy: 0.8103, Val Loss: 1.1889, Val Accuracy: 0.7188 Epoch 6683/10000, Train Loss: 1.1018, Train Accuracy: 0.8158, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6684/10000, Train Loss: 1.0943, Train Accuracy: 0.8248, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6685/10000, Train Loss: 1.1063, Train Accuracy: 0.8136, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6686/10000, Train Loss: 1.0964, Train Accuracy: 0.8214, Val Loss: 1.1894, Val Accuracy: 0.7232 Epoch 6687/10000, Train Loss: 1.0997, Train Accuracy: 0.8203, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6688/10000, Train Loss: 1.0958, Train Accuracy: 0.8248, Val Loss: 1.1895, Val Accuracy: 0.7232 Epoch 6689/10000, Train Loss: 1.1062, Train Accuracy: 0.8025, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6690/10000, Train Loss: 1.1135, Train Accuracy: 0.8013, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6691/10000, Train Loss: 1.0990, Train Accuracy: 0.8214, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6692/10000, Train Loss: 1.0972, Train Accuracy: 0.8158, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6693/10000, Train Loss: 1.1005, Train Accuracy: 0.8103, Val Loss: 1.1894, Val Accuracy: 0.7232 Epoch 6694/10000, Train Loss: 1.1011, Train Accuracy: 0.8058, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6695/10000, Train Loss: 1.1073, Train Accuracy: 0.8058, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6696/10000, Train Loss: 1.0958, Train Accuracy: 0.8214, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6697/10000, Train Loss: 1.1159, Train Accuracy: 0.7946, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6698/10000, Train Loss: 1.1055, Train Accuracy: 0.8080, Val Loss: 1.1890, Val Accuracy: 0.7188 Epoch 6699/10000, Train Loss: 1.1003, Train Accuracy: 0.8125, Val Loss: 1.1889, Val Accuracy: 0.7188 Epoch 6700/10000, Train Loss: 1.0880, Train Accuracy: 0.8259, Val Loss: 1.1886, Val Accuracy: 0.7188 Epoch 6701/10000, Train Loss: 1.0989, Train Accuracy: 0.8092, Val Loss: 1.1888, Val Accuracy: 0.7188 Epoch 6702/10000, Train Loss: 1.0995, Train Accuracy: 0.8181, Val Loss: 1.1889, Val Accuracy: 0.7188 Epoch 6703/10000, Train Loss: 1.1020, Train Accuracy: 0.8125, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6704/10000, Train Loss: 1.0922, Train Accuracy: 0.8203, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6705/10000, Train Loss: 1.1079, Train Accuracy: 0.8025, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6706/10000, Train Loss: 1.0963, Train Accuracy: 0.8114, Val Loss: 1.1895, Val Accuracy: 0.7188 Epoch 6707/10000, Train Loss: 1.0935, Train Accuracy: 0.8281, Val Loss: 1.1890, Val Accuracy: 0.7188 Epoch 6708/10000, Train Loss: 1.1000, Train Accuracy: 0.8192, Val Loss: 1.1891, Val Accuracy: 0.7188 Epoch 6709/10000, Train Loss: 1.0874, Train Accuracy: 0.8304, Val Loss: 1.1893, Val Accuracy: 0.7188 Epoch 6710/10000, Train Loss: 1.0926, Train Accuracy: 0.8225, Val Loss: 1.1891, Val Accuracy: 0.7188 Epoch 6711/10000, Train Loss: 1.1033, Train Accuracy: 0.8036, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6712/10000, Train Loss: 1.0971, Train Accuracy: 0.8170, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6713/10000, Train Loss: 1.0918, Train Accuracy: 0.8114, Val Loss: 1.1891, Val Accuracy: 0.7188 Epoch 6714/10000, Train Loss: 1.0953, Train Accuracy: 0.8125, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6715/10000, Train Loss: 1.0981, Train Accuracy: 0.8125, Val Loss: 1.1891, Val Accuracy: 0.7188 Epoch 6716/10000, Train Loss: 1.0901, Train Accuracy: 0.8292, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6717/10000, Train Loss: 1.1055, Train Accuracy: 0.8080, Val Loss: 1.1895, Val Accuracy: 0.7188 Epoch 6718/10000, Train Loss: 1.0993, Train Accuracy: 0.8181, Val Loss: 1.1893, Val Accuracy: 0.7188 Epoch 6719/10000, Train Loss: 1.0969, Train Accuracy: 0.8181, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6720/10000, Train Loss: 1.0994, Train Accuracy: 0.8203, Val Loss: 1.1888, Val Accuracy: 0.7188 Epoch 6721/10000, Train Loss: 1.1139, Train Accuracy: 0.7980, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6722/10000, Train Loss: 1.0972, Train Accuracy: 0.8125, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6723/10000, Train Loss: 1.0737, Train Accuracy: 0.8438, Val Loss: 1.1885, Val Accuracy: 0.7232 Epoch 6724/10000, Train Loss: 1.0821, Train Accuracy: 0.8371, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6725/10000, Train Loss: 1.1051, Train Accuracy: 0.8058, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6726/10000, Train Loss: 1.1054, Train Accuracy: 0.8080, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6727/10000, Train Loss: 1.0981, Train Accuracy: 0.8136, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6728/10000, Train Loss: 1.0835, Train Accuracy: 0.8348, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6729/10000, Train Loss: 1.0917, Train Accuracy: 0.8248, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6730/10000, Train Loss: 1.0865, Train Accuracy: 0.8292, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6731/10000, Train Loss: 1.0982, Train Accuracy: 0.8058, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6732/10000, Train Loss: 1.0976, Train Accuracy: 0.8158, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6733/10000, Train Loss: 1.1105, Train Accuracy: 0.8080, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6734/10000, Train Loss: 1.0899, Train Accuracy: 0.8214, Val Loss: 1.1884, Val Accuracy: 0.7232 Epoch 6735/10000, Train Loss: 1.0992, Train Accuracy: 0.8237, Val Loss: 1.1885, Val Accuracy: 0.7232 Epoch 6736/10000, Train Loss: 1.0735, Train Accuracy: 0.8460, Val Loss: 1.1884, Val Accuracy: 0.7232 Epoch 6737/10000, Train Loss: 1.0981, Train Accuracy: 0.8192, Val Loss: 1.1883, Val Accuracy: 0.7232 Epoch 6738/10000, Train Loss: 1.0947, Train Accuracy: 0.8237, Val Loss: 1.1885, Val Accuracy: 0.7232 Epoch 6739/10000, Train Loss: 1.0984, Train Accuracy: 0.8225, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6740/10000, Train Loss: 1.0926, Train Accuracy: 0.8270, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6741/10000, Train Loss: 1.0817, Train Accuracy: 0.8371, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6742/10000, Train Loss: 1.1069, Train Accuracy: 0.8092, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6743/10000, Train Loss: 1.1000, Train Accuracy: 0.8092, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6744/10000, Train Loss: 1.0929, Train Accuracy: 0.8192, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6745/10000, Train Loss: 1.1065, Train Accuracy: 0.8147, Val Loss: 1.1895, Val Accuracy: 0.7232 Epoch 6746/10000, Train Loss: 1.0957, Train Accuracy: 0.8259, Val Loss: 1.1895, Val Accuracy: 0.7232 Epoch 6747/10000, Train Loss: 1.1082, Train Accuracy: 0.8092, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6748/10000, Train Loss: 1.0792, Train Accuracy: 0.8393, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6749/10000, Train Loss: 1.1000, Train Accuracy: 0.8069, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6750/10000, Train Loss: 1.0971, Train Accuracy: 0.8147, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6751/10000, Train Loss: 1.0918, Train Accuracy: 0.8237, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6752/10000, Train Loss: 1.0902, Train Accuracy: 0.8270, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6753/10000, Train Loss: 1.0904, Train Accuracy: 0.8170, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6754/10000, Train Loss: 1.0995, Train Accuracy: 0.8103, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6755/10000, Train Loss: 1.1097, Train Accuracy: 0.8036, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6756/10000, Train Loss: 1.0967, Train Accuracy: 0.8114, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6757/10000, Train Loss: 1.1095, Train Accuracy: 0.8080, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6758/10000, Train Loss: 1.0982, Train Accuracy: 0.8192, Val Loss: 1.1888, Val Accuracy: 0.7232 Epoch 6759/10000, Train Loss: 1.0992, Train Accuracy: 0.8147, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6760/10000, Train Loss: 1.0786, Train Accuracy: 0.8415, Val Loss: 1.1884, Val Accuracy: 0.7232 Epoch 6761/10000, Train Loss: 1.0982, Train Accuracy: 0.8158, Val Loss: 1.1885, Val Accuracy: 0.7232 Epoch 6762/10000, Train Loss: 1.0957, Train Accuracy: 0.8158, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6763/10000, Train Loss: 1.1127, Train Accuracy: 0.8047, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6764/10000, Train Loss: 1.1031, Train Accuracy: 0.8058, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6765/10000, Train Loss: 1.0943, Train Accuracy: 0.8192, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6766/10000, Train Loss: 1.0789, Train Accuracy: 0.8404, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6767/10000, Train Loss: 1.1139, Train Accuracy: 0.7946, Val Loss: 1.1888, Val Accuracy: 0.7232 Epoch 6768/10000, Train Loss: 1.0904, Train Accuracy: 0.8248, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6769/10000, Train Loss: 1.1045, Train Accuracy: 0.8036, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6770/10000, Train Loss: 1.0911, Train Accuracy: 0.8225, Val Loss: 1.1888, Val Accuracy: 0.7232 Epoch 6771/10000, Train Loss: 1.1013, Train Accuracy: 0.8114, Val Loss: 1.1888, Val Accuracy: 0.7232 Epoch 6772/10000, Train Loss: 1.0984, Train Accuracy: 0.8192, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6773/10000, Train Loss: 1.1140, Train Accuracy: 0.8036, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6774/10000, Train Loss: 1.0916, Train Accuracy: 0.8248, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6775/10000, Train Loss: 1.0984, Train Accuracy: 0.8203, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6776/10000, Train Loss: 1.1052, Train Accuracy: 0.8092, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6777/10000, Train Loss: 1.0921, Train Accuracy: 0.8237, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6778/10000, Train Loss: 1.0901, Train Accuracy: 0.8248, Val Loss: 1.1894, Val Accuracy: 0.7232 Epoch 6779/10000, Train Loss: 1.0901, Train Accuracy: 0.8292, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6780/10000, Train Loss: 1.0823, Train Accuracy: 0.8326, Val Loss: 1.1893, Val Accuracy: 0.7232 Epoch 6781/10000, Train Loss: 1.0848, Train Accuracy: 0.8326, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6782/10000, Train Loss: 1.0823, Train Accuracy: 0.8359, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6783/10000, Train Loss: 1.0954, Train Accuracy: 0.8136, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6784/10000, Train Loss: 1.1063, Train Accuracy: 0.8092, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6785/10000, Train Loss: 1.0848, Train Accuracy: 0.8315, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6786/10000, Train Loss: 1.1077, Train Accuracy: 0.8103, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6787/10000, Train Loss: 1.1054, Train Accuracy: 0.8069, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6788/10000, Train Loss: 1.0824, Train Accuracy: 0.8304, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6789/10000, Train Loss: 1.0924, Train Accuracy: 0.8248, Val Loss: 1.1892, Val Accuracy: 0.7232 Epoch 6790/10000, Train Loss: 1.0990, Train Accuracy: 0.8170, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6791/10000, Train Loss: 1.0972, Train Accuracy: 0.8203, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6792/10000, Train Loss: 1.0851, Train Accuracy: 0.8315, Val Loss: 1.1890, Val Accuracy: 0.7232 Epoch 6793/10000, Train Loss: 1.0941, Train Accuracy: 0.8237, Val Loss: 1.1891, Val Accuracy: 0.7232 Epoch 6794/10000, Train Loss: 1.0990, Train Accuracy: 0.8114, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6795/10000, Train Loss: 1.0793, Train Accuracy: 0.8348, Val Loss: 1.1893, Val Accuracy: 0.7188 Epoch 6796/10000, Train Loss: 1.0896, Train Accuracy: 0.8225, Val Loss: 1.1895, Val Accuracy: 0.7188 Epoch 6797/10000, Train Loss: 1.0923, Train Accuracy: 0.8326, Val Loss: 1.1895, Val Accuracy: 0.7188 Epoch 6798/10000, Train Loss: 1.0946, Train Accuracy: 0.8203, Val Loss: 1.1895, Val Accuracy: 0.7188 Epoch 6799/10000, Train Loss: 1.0958, Train Accuracy: 0.8181, Val Loss: 1.1893, Val Accuracy: 0.7143 Epoch 6800/10000, Train Loss: 1.0945, Train Accuracy: 0.8114, Val Loss: 1.1891, Val Accuracy: 0.7143 Epoch 6801/10000, Train Loss: 1.0914, Train Accuracy: 0.8214, Val Loss: 1.1891, Val Accuracy: 0.7188 Epoch 6802/10000, Train Loss: 1.0898, Train Accuracy: 0.8248, Val Loss: 1.1892, Val Accuracy: 0.7188 Epoch 6803/10000, Train Loss: 1.1035, Train Accuracy: 0.8058, Val Loss: 1.1896, Val Accuracy: 0.7188 Epoch 6804/10000, Train Loss: 1.0979, Train Accuracy: 0.8147, Val Loss: 1.1896, Val Accuracy: 0.7098 Epoch 6805/10000, Train Loss: 1.1054, Train Accuracy: 0.8058, Val Loss: 1.1899, Val Accuracy: 0.7098 Epoch 6806/10000, Train Loss: 1.0897, Train Accuracy: 0.8304, Val Loss: 1.1896, Val Accuracy: 0.7098 Epoch 6807/10000, Train Loss: 1.0927, Train Accuracy: 0.8158, Val Loss: 1.1898, Val Accuracy: 0.7098 Epoch 6808/10000, Train Loss: 1.0899, Train Accuracy: 0.8214, Val Loss: 1.1898, Val Accuracy: 0.7098 Epoch 6809/10000, Train Loss: 1.1030, Train Accuracy: 0.8092, Val Loss: 1.1900, Val Accuracy: 0.7098 Epoch 6810/10000, Train Loss: 1.0932, Train Accuracy: 0.8203, Val Loss: 1.1896, Val Accuracy: 0.7098 Epoch 6811/10000, Train Loss: 1.0912, Train Accuracy: 0.8292, Val Loss: 1.1896, Val Accuracy: 0.7143 Epoch 6812/10000, Train Loss: 1.0869, Train Accuracy: 0.8304, Val Loss: 1.1898, Val Accuracy: 0.7098 Epoch 6813/10000, Train Loss: 1.1028, Train Accuracy: 0.8092, Val Loss: 1.1898, Val Accuracy: 0.7098 Epoch 6814/10000, Train Loss: 1.0851, Train Accuracy: 0.8382, Val Loss: 1.1898, Val Accuracy: 0.7098 Epoch 6815/10000, Train Loss: 1.0944, Train Accuracy: 0.8170, Val Loss: 1.1896, Val Accuracy: 0.7143 Epoch 6816/10000, Train Loss: 1.0925, Train Accuracy: 0.8225, Val Loss: 1.1892, Val Accuracy: 0.7143 Epoch 6817/10000, Train Loss: 1.0884, Train Accuracy: 0.8259, Val Loss: 1.1890, Val Accuracy: 0.7143 Epoch 6818/10000, Train Loss: 1.0921, Train Accuracy: 0.8203, Val Loss: 1.1890, Val Accuracy: 0.7098 Epoch 6819/10000, Train Loss: 1.0859, Train Accuracy: 0.8326, Val Loss: 1.1892, Val Accuracy: 0.7098 Epoch 6820/10000, Train Loss: 1.1060, Train Accuracy: 0.8047, Val Loss: 1.1894, Val Accuracy: 0.7098 Epoch 6821/10000, Train Loss: 1.0985, Train Accuracy: 0.8192, Val Loss: 1.1893, Val Accuracy: 0.7143 Epoch 6822/10000, Train Loss: 1.1085, Train Accuracy: 0.8058, Val Loss: 1.1891, Val Accuracy: 0.7098 Epoch 6823/10000, Train Loss: 1.0770, Train Accuracy: 0.8348, Val Loss: 1.1888, Val Accuracy: 0.7098 Epoch 6824/10000, Train Loss: 1.0988, Train Accuracy: 0.8114, Val Loss: 1.1888, Val Accuracy: 0.7098 Epoch 6825/10000, Train Loss: 1.0941, Train Accuracy: 0.8214, Val Loss: 1.1885, Val Accuracy: 0.7143 Epoch 6826/10000, Train Loss: 1.0963, Train Accuracy: 0.8203, Val Loss: 1.1884, Val Accuracy: 0.7143 Epoch 6827/10000, Train Loss: 1.0862, Train Accuracy: 0.8326, Val Loss: 1.1883, Val Accuracy: 0.7143 Epoch 6828/10000, Train Loss: 1.1055, Train Accuracy: 0.8002, Val Loss: 1.1886, Val Accuracy: 0.7188 Epoch 6829/10000, Train Loss: 1.0844, Train Accuracy: 0.8337, Val Loss: 1.1883, Val Accuracy: 0.7188 Epoch 6830/10000, Train Loss: 1.0901, Train Accuracy: 0.8237, Val Loss: 1.1885, Val Accuracy: 0.7143 Epoch 6831/10000, Train Loss: 1.0999, Train Accuracy: 0.8147, Val Loss: 1.1884, Val Accuracy: 0.7188 Epoch 6832/10000, Train Loss: 1.0836, Train Accuracy: 0.8292, Val Loss: 1.1884, Val Accuracy: 0.7232 Epoch 6833/10000, Train Loss: 1.0922, Train Accuracy: 0.8170, Val Loss: 1.1881, Val Accuracy: 0.7232 Epoch 6834/10000, Train Loss: 1.0991, Train Accuracy: 0.8136, Val Loss: 1.1884, Val Accuracy: 0.7321 Epoch 6835/10000, Train Loss: 1.0982, Train Accuracy: 0.8170, Val Loss: 1.1887, Val Accuracy: 0.7277 Epoch 6836/10000, Train Loss: 1.0998, Train Accuracy: 0.8158, Val Loss: 1.1885, Val Accuracy: 0.7232 Epoch 6837/10000, Train Loss: 1.0826, Train Accuracy: 0.8248, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6838/10000, Train Loss: 1.0932, Train Accuracy: 0.8259, Val Loss: 1.1889, Val Accuracy: 0.7232 Epoch 6839/10000, Train Loss: 1.0877, Train Accuracy: 0.8270, Val Loss: 1.1888, Val Accuracy: 0.7188 Epoch 6840/10000, Train Loss: 1.0842, Train Accuracy: 0.8225, Val Loss: 1.1886, Val Accuracy: 0.7143 Epoch 6841/10000, Train Loss: 1.0925, Train Accuracy: 0.8237, Val Loss: 1.1885, Val Accuracy: 0.7188 Epoch 6842/10000, Train Loss: 1.0898, Train Accuracy: 0.8237, Val Loss: 1.1886, Val Accuracy: 0.7188 Epoch 6843/10000, Train Loss: 1.1054, Train Accuracy: 0.8147, Val Loss: 1.1887, Val Accuracy: 0.7277 Epoch 6844/10000, Train Loss: 1.0985, Train Accuracy: 0.8103, Val Loss: 1.1889, Val Accuracy: 0.7277 Epoch 6845/10000, Train Loss: 1.0903, Train Accuracy: 0.8270, Val Loss: 1.1886, Val Accuracy: 0.7232 Epoch 6846/10000, Train Loss: 1.0755, Train Accuracy: 0.8460, Val Loss: 1.1885, Val Accuracy: 0.7277 Epoch 6847/10000, Train Loss: 1.0962, Train Accuracy: 0.8114, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6848/10000, Train Loss: 1.1034, Train Accuracy: 0.8092, Val Loss: 1.1886, Val Accuracy: 0.7277 Epoch 6849/10000, Train Loss: 1.0982, Train Accuracy: 0.8192, Val Loss: 1.1887, Val Accuracy: 0.7232 Epoch 6850/10000, Train Loss: 1.0840, Train Accuracy: 0.8326, Val Loss: 1.1885, Val Accuracy: 0.7232 Epoch 6851/10000, Train Loss: 1.0906, Train Accuracy: 0.8147, Val Loss: 1.1882, Val Accuracy: 0.7232 Epoch 6852/10000, Train Loss: 1.0966, Train Accuracy: 0.8147, Val Loss: 1.1881, Val Accuracy: 0.7188 Epoch 6853/10000, Train Loss: 1.0972, Train Accuracy: 0.8158, Val Loss: 1.1883, Val Accuracy: 0.7188 Epoch 6854/10000, Train Loss: 1.0917, Train Accuracy: 0.8270, Val Loss: 1.1882, Val Accuracy: 0.7143 Epoch 6855/10000, Train Loss: 1.1029, Train Accuracy: 0.8047, Val Loss: 1.1883, Val Accuracy: 0.7143 Epoch 6856/10000, Train Loss: 1.0817, Train Accuracy: 0.8348, Val Loss: 1.1881, Val Accuracy: 0.7143 Epoch 6857/10000, Train Loss: 1.0843, Train Accuracy: 0.8326, Val Loss: 1.1881, Val Accuracy: 0.7143 Epoch 6858/10000, Train Loss: 1.0781, Train Accuracy: 0.8415, Val Loss: 1.1880, Val Accuracy: 0.7143 Epoch 6859/10000, Train Loss: 1.0980, Train Accuracy: 0.8125, Val Loss: 1.1878, Val Accuracy: 0.7143 Epoch 6860/10000, Train Loss: 1.0985, Train Accuracy: 0.8181, Val Loss: 1.1878, Val Accuracy: 0.7188 Epoch 6861/10000, Train Loss: 1.0928, Train Accuracy: 0.8170, Val Loss: 1.1878, Val Accuracy: 0.7232 Epoch 6862/10000, Train Loss: 1.0917, Train Accuracy: 0.8214, Val Loss: 1.1879, Val Accuracy: 0.7232 Epoch 6863/10000, Train Loss: 1.0979, Train Accuracy: 0.8203, Val Loss: 1.1877, Val Accuracy: 0.7232 Epoch 6864/10000, Train Loss: 1.0896, Train Accuracy: 0.8170, Val Loss: 1.1878, Val Accuracy: 0.7232 Epoch 6865/10000, Train Loss: 1.1026, Train Accuracy: 0.8092, Val Loss: 1.1879, Val Accuracy: 0.7232 Epoch 6866/10000, Train Loss: 1.1049, Train Accuracy: 0.8158, Val Loss: 1.1877, Val Accuracy: 0.7188 Epoch 6867/10000, Train Loss: 1.1022, Train Accuracy: 0.8047, Val Loss: 1.1874, Val Accuracy: 0.7188 Epoch 6868/10000, Train Loss: 1.0875, Train Accuracy: 0.8203, Val Loss: 1.1874, Val Accuracy: 0.7188 Epoch 6869/10000, Train Loss: 1.0971, Train Accuracy: 0.8080, Val Loss: 1.1876, Val Accuracy: 0.7188 Epoch 6870/10000, Train Loss: 1.0937, Train Accuracy: 0.8248, Val Loss: 1.1879, Val Accuracy: 0.7188 Epoch 6871/10000, Train Loss: 1.1074, Train Accuracy: 0.7980, Val Loss: 1.1878, Val Accuracy: 0.7188 Epoch 6872/10000, Train Loss: 1.0973, Train Accuracy: 0.8147, Val Loss: 1.1875, Val Accuracy: 0.7188 Epoch 6873/10000, Train Loss: 1.0928, Train Accuracy: 0.8192, Val Loss: 1.1880, Val Accuracy: 0.7188 Epoch 6874/10000, Train Loss: 1.0802, Train Accuracy: 0.8326, Val Loss: 1.1881, Val Accuracy: 0.7143 Epoch 6875/10000, Train Loss: 1.1029, Train Accuracy: 0.8114, Val Loss: 1.1882, Val Accuracy: 0.7098 Epoch 6876/10000, Train Loss: 1.1028, Train Accuracy: 0.8080, Val Loss: 1.1880, Val Accuracy: 0.7098 Epoch 6877/10000, Train Loss: 1.0847, Train Accuracy: 0.8337, Val Loss: 1.1879, Val Accuracy: 0.7098 Epoch 6878/10000, Train Loss: 1.0971, Train Accuracy: 0.8158, Val Loss: 1.1880, Val Accuracy: 0.7143 Epoch 6879/10000, Train Loss: 1.0949, Train Accuracy: 0.8214, Val Loss: 1.1881, Val Accuracy: 0.7098 Epoch 6880/10000, Train Loss: 1.0982, Train Accuracy: 0.8158, Val Loss: 1.1882, Val Accuracy: 0.7098 Epoch 6881/10000, Train Loss: 1.0879, Train Accuracy: 0.8170, Val Loss: 1.1886, Val Accuracy: 0.7098 Epoch 6882/10000, Train Loss: 1.0994, Train Accuracy: 0.8103, Val Loss: 1.1884, Val Accuracy: 0.7098 Epoch 6883/10000, Train Loss: 1.0784, Train Accuracy: 0.8382, Val Loss: 1.1886, Val Accuracy: 0.7143 Epoch 6884/10000, Train Loss: 1.0871, Train Accuracy: 0.8315, Val Loss: 1.1885, Val Accuracy: 0.7143 Epoch 6885/10000, Train Loss: 1.1034, Train Accuracy: 0.8058, Val Loss: 1.1884, Val Accuracy: 0.7143 Epoch 6886/10000, Train Loss: 1.0802, Train Accuracy: 0.8371, Val Loss: 1.1882, Val Accuracy: 0.7188 Epoch 6887/10000, Train Loss: 1.1016, Train Accuracy: 0.8103, Val Loss: 1.1883, Val Accuracy: 0.7188 Epoch 6888/10000, Train Loss: 1.0812, Train Accuracy: 0.8326, Val Loss: 1.1882, Val Accuracy: 0.7143 Epoch 6889/10000, Train Loss: 1.0857, Train Accuracy: 0.8192, Val Loss: 1.1882, Val Accuracy: 0.7188 Epoch 6890/10000, Train Loss: 1.0903, Train Accuracy: 0.8270, Val Loss: 1.1883, Val Accuracy: 0.7188 Epoch 6891/10000, Train Loss: 1.0871, Train Accuracy: 0.8281, Val Loss: 1.1881, Val Accuracy: 0.7188 Epoch 6892/10000, Train Loss: 1.0948, Train Accuracy: 0.8103, Val Loss: 1.1877, Val Accuracy: 0.7188 Epoch 6893/10000, Train Loss: 1.0818, Train Accuracy: 0.8348, Val Loss: 1.1879, Val Accuracy: 0.7188 Epoch 6894/10000, Train Loss: 1.0943, Train Accuracy: 0.8214, Val Loss: 1.1879, Val Accuracy: 0.7188 Epoch 6895/10000, Train Loss: 1.0944, Train Accuracy: 0.8103, Val Loss: 1.1880, Val Accuracy: 0.7188 Epoch 6896/10000, Train Loss: 1.0931, Train Accuracy: 0.8259, Val Loss: 1.1877, Val Accuracy: 0.7188 Epoch 6897/10000, Train Loss: 1.0907, Train Accuracy: 0.8203, Val Loss: 1.1878, Val Accuracy: 0.7143 Epoch 6898/10000, Train Loss: 1.0875, Train Accuracy: 0.8225, Val Loss: 1.1880, Val Accuracy: 0.7188 Epoch 6899/10000, Train Loss: 1.0844, Train Accuracy: 0.8326, Val Loss: 1.1879, Val Accuracy: 0.7143 Epoch 6900/10000, Train Loss: 1.0890, Train Accuracy: 0.8237, Val Loss: 1.1876, Val Accuracy: 0.7143 Epoch 6901/10000, Train Loss: 1.0962, Train Accuracy: 0.8114, Val Loss: 1.1877, Val Accuracy: 0.7188 Epoch 6902/10000, Train Loss: 1.0899, Train Accuracy: 0.8270, Val Loss: 1.1881, Val Accuracy: 0.7188 Epoch 6903/10000, Train Loss: 1.0885, Train Accuracy: 0.8181, Val Loss: 1.1876, Val Accuracy: 0.7188 Epoch 6904/10000, Train Loss: 1.0885, Train Accuracy: 0.8192, Val Loss: 1.1876, Val Accuracy: 0.7143 Epoch 6905/10000, Train Loss: 1.0945, Train Accuracy: 0.8147, Val Loss: 1.1876, Val Accuracy: 0.7143 Epoch 6906/10000, Train Loss: 1.0975, Train Accuracy: 0.8147, Val Loss: 1.1876, Val Accuracy: 0.7143 Epoch 6907/10000, Train Loss: 1.0941, Train Accuracy: 0.8237, Val Loss: 1.1875, Val Accuracy: 0.7143 Epoch 6908/10000, Train Loss: 1.0924, Train Accuracy: 0.8181, Val Loss: 1.1875, Val Accuracy: 0.7143 Epoch 6909/10000, Train Loss: 1.0871, Train Accuracy: 0.8248, Val Loss: 1.1876, Val Accuracy: 0.7143 Epoch 6910/10000, Train Loss: 1.0894, Train Accuracy: 0.8292, Val Loss: 1.1876, Val Accuracy: 0.7143 Epoch 6911/10000, Train Loss: 1.0966, Train Accuracy: 0.8181, Val Loss: 1.1875, Val Accuracy: 0.7143 Epoch 6912/10000, Train Loss: 1.0865, Train Accuracy: 0.8225, Val Loss: 1.1875, Val Accuracy: 0.7188 Epoch 6913/10000, Train Loss: 1.0983, Train Accuracy: 0.8080, Val Loss: 1.1873, Val Accuracy: 0.7232 Epoch 6914/10000, Train Loss: 1.0896, Train Accuracy: 0.8136, Val Loss: 1.1874, Val Accuracy: 0.7188 Epoch 6915/10000, Train Loss: 1.0857, Train Accuracy: 0.8304, Val Loss: 1.1875, Val Accuracy: 0.7232 Epoch 6916/10000, Train Loss: 1.0893, Train Accuracy: 0.8214, Val Loss: 1.1873, Val Accuracy: 0.7232 Epoch 6917/10000, Train Loss: 1.0765, Train Accuracy: 0.8404, Val Loss: 1.1877, Val Accuracy: 0.7232 Epoch 6918/10000, Train Loss: 1.0916, Train Accuracy: 0.8158, Val Loss: 1.1875, Val Accuracy: 0.7232 Epoch 6919/10000, Train Loss: 1.0840, Train Accuracy: 0.8304, Val Loss: 1.1874, Val Accuracy: 0.7232 Epoch 6920/10000, Train Loss: 1.0967, Train Accuracy: 0.8147, Val Loss: 1.1870, Val Accuracy: 0.7188 Epoch 6921/10000, Train Loss: 1.0873, Train Accuracy: 0.8203, Val Loss: 1.1871, Val Accuracy: 0.7232 Epoch 6922/10000, Train Loss: 1.0822, Train Accuracy: 0.8315, Val Loss: 1.1872, Val Accuracy: 0.7277 Epoch 6923/10000, Train Loss: 1.0805, Train Accuracy: 0.8359, Val Loss: 1.1874, Val Accuracy: 0.7232 Epoch 6924/10000, Train Loss: 1.0972, Train Accuracy: 0.8114, Val Loss: 1.1874, Val Accuracy: 0.7232 Epoch 6925/10000, Train Loss: 1.0922, Train Accuracy: 0.8259, Val Loss: 1.1873, Val Accuracy: 0.7188 Epoch 6926/10000, Train Loss: 1.0898, Train Accuracy: 0.8248, Val Loss: 1.1874, Val Accuracy: 0.7188 Epoch 6927/10000, Train Loss: 1.0862, Train Accuracy: 0.8292, Val Loss: 1.1871, Val Accuracy: 0.7188 Epoch 6928/10000, Train Loss: 1.1098, Train Accuracy: 0.7991, Val Loss: 1.1872, Val Accuracy: 0.7188 Epoch 6929/10000, Train Loss: 1.0935, Train Accuracy: 0.8237, Val Loss: 1.1872, Val Accuracy: 0.7188 Epoch 6930/10000, Train Loss: 1.0881, Train Accuracy: 0.8315, Val Loss: 1.1873, Val Accuracy: 0.7188 Epoch 6931/10000, Train Loss: 1.0743, Train Accuracy: 0.8404, Val Loss: 1.1872, Val Accuracy: 0.7188 Epoch 6932/10000, Train Loss: 1.0874, Train Accuracy: 0.8225, Val Loss: 1.1869, Val Accuracy: 0.7188 Epoch 6933/10000, Train Loss: 1.0868, Train Accuracy: 0.8315, Val Loss: 1.1868, Val Accuracy: 0.7232 Epoch 6934/10000, Train Loss: 1.0865, Train Accuracy: 0.8292, Val Loss: 1.1869, Val Accuracy: 0.7188 Epoch 6935/10000, Train Loss: 1.0902, Train Accuracy: 0.8192, Val Loss: 1.1870, Val Accuracy: 0.7188 Epoch 6936/10000, Train Loss: 1.0866, Train Accuracy: 0.8248, Val Loss: 1.1872, Val Accuracy: 0.7188 Epoch 6937/10000, Train Loss: 1.0877, Train Accuracy: 0.8225, Val Loss: 1.1868, Val Accuracy: 0.7188 Epoch 6938/10000, Train Loss: 1.0945, Train Accuracy: 0.8158, Val Loss: 1.1869, Val Accuracy: 0.7188 Epoch 6939/10000, Train Loss: 1.0807, Train Accuracy: 0.8292, Val Loss: 1.1869, Val Accuracy: 0.7232 Epoch 6940/10000, Train Loss: 1.0839, Train Accuracy: 0.8348, Val Loss: 1.1871, Val Accuracy: 0.7232 Epoch 6941/10000, Train Loss: 1.0915, Train Accuracy: 0.8203, Val Loss: 1.1868, Val Accuracy: 0.7232 Epoch 6942/10000, Train Loss: 1.0891, Train Accuracy: 0.8248, Val Loss: 1.1868, Val Accuracy: 0.7232 Epoch 6943/10000, Train Loss: 1.0954, Train Accuracy: 0.8158, Val Loss: 1.1868, Val Accuracy: 0.7232 Epoch 6944/10000, Train Loss: 1.0916, Train Accuracy: 0.8225, Val Loss: 1.1867, Val Accuracy: 0.7232 Epoch 6945/10000, Train Loss: 1.0842, Train Accuracy: 0.8337, Val Loss: 1.1865, Val Accuracy: 0.7232 Epoch 6946/10000, Train Loss: 1.0867, Train Accuracy: 0.8337, Val Loss: 1.1864, Val Accuracy: 0.7232 Epoch 6947/10000, Train Loss: 1.0741, Train Accuracy: 0.8438, Val Loss: 1.1864, Val Accuracy: 0.7232 Epoch 6948/10000, Train Loss: 1.1027, Train Accuracy: 0.8136, Val Loss: 1.1865, Val Accuracy: 0.7232 Epoch 6949/10000, Train Loss: 1.0763, Train Accuracy: 0.8382, Val Loss: 1.1865, Val Accuracy: 0.7232 Epoch 6950/10000, Train Loss: 1.0832, Train Accuracy: 0.8371, Val Loss: 1.1867, Val Accuracy: 0.7232 Epoch 6951/10000, Train Loss: 1.0860, Train Accuracy: 0.8281, Val Loss: 1.1866, Val Accuracy: 0.7277 Epoch 6952/10000, Train Loss: 1.0877, Train Accuracy: 0.8181, Val Loss: 1.1860, Val Accuracy: 0.7188 Epoch 6953/10000, Train Loss: 1.0838, Train Accuracy: 0.8259, Val Loss: 1.1858, Val Accuracy: 0.7188 Epoch 6954/10000, Train Loss: 1.0850, Train Accuracy: 0.8270, Val Loss: 1.1860, Val Accuracy: 0.7188 Epoch 6955/10000, Train Loss: 1.0945, Train Accuracy: 0.8203, Val Loss: 1.1861, Val Accuracy: 0.7188 Epoch 6956/10000, Train Loss: 1.0921, Train Accuracy: 0.8237, Val Loss: 1.1860, Val Accuracy: 0.7188 Epoch 6957/10000, Train Loss: 1.0889, Train Accuracy: 0.8214, Val Loss: 1.1859, Val Accuracy: 0.7188 Epoch 6958/10000, Train Loss: 1.0862, Train Accuracy: 0.8348, Val Loss: 1.1861, Val Accuracy: 0.7188 Epoch 6959/10000, Train Loss: 1.0839, Train Accuracy: 0.8359, Val Loss: 1.1861, Val Accuracy: 0.7188 Epoch 6960/10000, Train Loss: 1.0829, Train Accuracy: 0.8248, Val Loss: 1.1864, Val Accuracy: 0.7188 Epoch 6961/10000, Train Loss: 1.0937, Train Accuracy: 0.8214, Val Loss: 1.1863, Val Accuracy: 0.7188 Epoch 6962/10000, Train Loss: 1.0887, Train Accuracy: 0.8248, Val Loss: 1.1863, Val Accuracy: 0.7188 Epoch 6963/10000, Train Loss: 1.0933, Train Accuracy: 0.8125, Val Loss: 1.1864, Val Accuracy: 0.7188 Epoch 6964/10000, Train Loss: 1.1113, Train Accuracy: 0.8047, Val Loss: 1.1862, Val Accuracy: 0.7188 Epoch 6965/10000, Train Loss: 1.0774, Train Accuracy: 0.8393, Val Loss: 1.1864, Val Accuracy: 0.7188 Epoch 6966/10000, Train Loss: 1.0819, Train Accuracy: 0.8382, Val Loss: 1.1863, Val Accuracy: 0.7188 Epoch 6967/10000, Train Loss: 1.1037, Train Accuracy: 0.8058, Val Loss: 1.1862, Val Accuracy: 0.7232 Epoch 6968/10000, Train Loss: 1.0966, Train Accuracy: 0.8136, Val Loss: 1.1863, Val Accuracy: 0.7188 Epoch 6969/10000, Train Loss: 1.0903, Train Accuracy: 0.8304, Val Loss: 1.1865, Val Accuracy: 0.7232 Epoch 6970/10000, Train Loss: 1.0937, Train Accuracy: 0.8225, Val Loss: 1.1865, Val Accuracy: 0.7232 Epoch 6971/10000, Train Loss: 1.0830, Train Accuracy: 0.8382, Val Loss: 1.1863, Val Accuracy: 0.7232 Epoch 6972/10000, Train Loss: 1.0890, Train Accuracy: 0.8237, Val Loss: 1.1861, Val Accuracy: 0.7232 Epoch 6973/10000, Train Loss: 1.0815, Train Accuracy: 0.8270, Val Loss: 1.1862, Val Accuracy: 0.7232 Epoch 6974/10000, Train Loss: 1.0883, Train Accuracy: 0.8225, Val Loss: 1.1862, Val Accuracy: 0.7277 Epoch 6975/10000, Train Loss: 1.0932, Train Accuracy: 0.8203, Val Loss: 1.1860, Val Accuracy: 0.7232 Epoch 6976/10000, Train Loss: 1.0891, Train Accuracy: 0.8170, Val Loss: 1.1861, Val Accuracy: 0.7232 Epoch 6977/10000, Train Loss: 1.0834, Train Accuracy: 0.8203, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 6978/10000, Train Loss: 1.0899, Train Accuracy: 0.8292, Val Loss: 1.1856, Val Accuracy: 0.7277 Epoch 6979/10000, Train Loss: 1.0996, Train Accuracy: 0.8214, Val Loss: 1.1857, Val Accuracy: 0.7277 Epoch 6980/10000, Train Loss: 1.0935, Train Accuracy: 0.8170, Val Loss: 1.1855, Val Accuracy: 0.7277 Epoch 6981/10000, Train Loss: 1.0879, Train Accuracy: 0.8348, Val Loss: 1.1855, Val Accuracy: 0.7321 Epoch 6982/10000, Train Loss: 1.0947, Train Accuracy: 0.8181, Val Loss: 1.1856, Val Accuracy: 0.7321 Epoch 6983/10000, Train Loss: 1.0893, Train Accuracy: 0.8225, Val Loss: 1.1855, Val Accuracy: 0.7321 Epoch 6984/10000, Train Loss: 1.0857, Train Accuracy: 0.8225, Val Loss: 1.1856, Val Accuracy: 0.7321 Epoch 6985/10000, Train Loss: 1.0902, Train Accuracy: 0.8281, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 6986/10000, Train Loss: 1.0858, Train Accuracy: 0.8337, Val Loss: 1.1860, Val Accuracy: 0.7188 Epoch 6987/10000, Train Loss: 1.0855, Train Accuracy: 0.8225, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 6988/10000, Train Loss: 1.0874, Train Accuracy: 0.8270, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 6989/10000, Train Loss: 1.1033, Train Accuracy: 0.8047, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 6990/10000, Train Loss: 1.0845, Train Accuracy: 0.8337, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 6991/10000, Train Loss: 1.0889, Train Accuracy: 0.8237, Val Loss: 1.1856, Val Accuracy: 0.7188 Epoch 6992/10000, Train Loss: 1.0886, Train Accuracy: 0.8304, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 6993/10000, Train Loss: 1.0914, Train Accuracy: 0.8259, Val Loss: 1.1856, Val Accuracy: 0.7277 Epoch 6994/10000, Train Loss: 1.0922, Train Accuracy: 0.8136, Val Loss: 1.1856, Val Accuracy: 0.7277 Epoch 6995/10000, Train Loss: 1.0882, Train Accuracy: 0.8292, Val Loss: 1.1854, Val Accuracy: 0.7232 Epoch 6996/10000, Train Loss: 1.0834, Train Accuracy: 0.8259, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 6997/10000, Train Loss: 1.0887, Train Accuracy: 0.8214, Val Loss: 1.1853, Val Accuracy: 0.7188 Epoch 6998/10000, Train Loss: 1.0909, Train Accuracy: 0.8181, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 6999/10000, Train Loss: 1.0903, Train Accuracy: 0.8270, Val Loss: 1.1851, Val Accuracy: 0.7143 Epoch 7000/10000, Train Loss: 1.0894, Train Accuracy: 0.8259, Val Loss: 1.1852, Val Accuracy: 0.7143 Epoch 7001/10000, Train Loss: 1.0833, Train Accuracy: 0.8359, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7002/10000, Train Loss: 1.0959, Train Accuracy: 0.8158, Val Loss: 1.1852, Val Accuracy: 0.7143 Epoch 7003/10000, Train Loss: 1.0858, Train Accuracy: 0.8292, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7004/10000, Train Loss: 1.0778, Train Accuracy: 0.8304, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7005/10000, Train Loss: 1.0902, Train Accuracy: 0.8259, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7006/10000, Train Loss: 1.0824, Train Accuracy: 0.8237, Val Loss: 1.1848, Val Accuracy: 0.7188 Epoch 7007/10000, Train Loss: 1.0952, Train Accuracy: 0.8125, Val Loss: 1.1846, Val Accuracy: 0.7143 Epoch 7008/10000, Train Loss: 1.0745, Train Accuracy: 0.8382, Val Loss: 1.1847, Val Accuracy: 0.7188 Epoch 7009/10000, Train Loss: 1.0831, Train Accuracy: 0.8348, Val Loss: 1.1848, Val Accuracy: 0.7143 Epoch 7010/10000, Train Loss: 1.0933, Train Accuracy: 0.8103, Val Loss: 1.1849, Val Accuracy: 0.7143 Epoch 7011/10000, Train Loss: 1.0917, Train Accuracy: 0.8203, Val Loss: 1.1851, Val Accuracy: 0.7143 Epoch 7012/10000, Train Loss: 1.0889, Train Accuracy: 0.8192, Val Loss: 1.1853, Val Accuracy: 0.7188 Epoch 7013/10000, Train Loss: 1.0907, Train Accuracy: 0.8225, Val Loss: 1.1854, Val Accuracy: 0.7188 Epoch 7014/10000, Train Loss: 1.0807, Train Accuracy: 0.8337, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7015/10000, Train Loss: 1.0854, Train Accuracy: 0.8281, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7016/10000, Train Loss: 1.0825, Train Accuracy: 0.8359, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7017/10000, Train Loss: 1.0913, Train Accuracy: 0.8270, Val Loss: 1.1851, Val Accuracy: 0.7143 Epoch 7018/10000, Train Loss: 1.0841, Train Accuracy: 0.8359, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7019/10000, Train Loss: 1.0795, Train Accuracy: 0.8371, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7020/10000, Train Loss: 1.0891, Train Accuracy: 0.8203, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7021/10000, Train Loss: 1.0960, Train Accuracy: 0.8170, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7022/10000, Train Loss: 1.0940, Train Accuracy: 0.8136, Val Loss: 1.1855, Val Accuracy: 0.7143 Epoch 7023/10000, Train Loss: 1.0757, Train Accuracy: 0.8348, Val Loss: 1.1854, Val Accuracy: 0.7188 Epoch 7024/10000, Train Loss: 1.0826, Train Accuracy: 0.8304, Val Loss: 1.1853, Val Accuracy: 0.7277 Epoch 7025/10000, Train Loss: 1.0865, Train Accuracy: 0.8304, Val Loss: 1.1854, Val Accuracy: 0.7188 Epoch 7026/10000, Train Loss: 1.1007, Train Accuracy: 0.8047, Val Loss: 1.1856, Val Accuracy: 0.7188 Epoch 7027/10000, Train Loss: 1.0800, Train Accuracy: 0.8348, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7028/10000, Train Loss: 1.0970, Train Accuracy: 0.8170, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7029/10000, Train Loss: 1.0676, Train Accuracy: 0.8549, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 7030/10000, Train Loss: 1.0864, Train Accuracy: 0.8304, Val Loss: 1.1852, Val Accuracy: 0.7143 Epoch 7031/10000, Train Loss: 1.0880, Train Accuracy: 0.8281, Val Loss: 1.1850, Val Accuracy: 0.7143 Epoch 7032/10000, Train Loss: 1.0857, Train Accuracy: 0.8393, Val Loss: 1.1850, Val Accuracy: 0.7188 Epoch 7033/10000, Train Loss: 1.0995, Train Accuracy: 0.8125, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7034/10000, Train Loss: 1.0880, Train Accuracy: 0.8225, Val Loss: 1.1851, Val Accuracy: 0.7277 Epoch 7035/10000, Train Loss: 1.0764, Train Accuracy: 0.8404, Val Loss: 1.1848, Val Accuracy: 0.7232 Epoch 7036/10000, Train Loss: 1.0923, Train Accuracy: 0.8214, Val Loss: 1.1850, Val Accuracy: 0.7277 Epoch 7037/10000, Train Loss: 1.0940, Train Accuracy: 0.8069, Val Loss: 1.1849, Val Accuracy: 0.7188 Epoch 7038/10000, Train Loss: 1.0983, Train Accuracy: 0.8103, Val Loss: 1.1850, Val Accuracy: 0.7232 Epoch 7039/10000, Train Loss: 1.0807, Train Accuracy: 0.8337, Val Loss: 1.1847, Val Accuracy: 0.7232 Epoch 7040/10000, Train Loss: 1.1005, Train Accuracy: 0.8114, Val Loss: 1.1847, Val Accuracy: 0.7232 Epoch 7041/10000, Train Loss: 1.0943, Train Accuracy: 0.8237, Val Loss: 1.1848, Val Accuracy: 0.7232 Epoch 7042/10000, Train Loss: 1.0746, Train Accuracy: 0.8404, Val Loss: 1.1848, Val Accuracy: 0.7232 Epoch 7043/10000, Train Loss: 1.0751, Train Accuracy: 0.8460, Val Loss: 1.1849, Val Accuracy: 0.7232 Epoch 7044/10000, Train Loss: 1.0973, Train Accuracy: 0.8214, Val Loss: 1.1849, Val Accuracy: 0.7188 Epoch 7045/10000, Train Loss: 1.0879, Train Accuracy: 0.8237, Val Loss: 1.1851, Val Accuracy: 0.7188 Epoch 7046/10000, Train Loss: 1.0888, Train Accuracy: 0.8259, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7047/10000, Train Loss: 1.0860, Train Accuracy: 0.8237, Val Loss: 1.1854, Val Accuracy: 0.7188 Epoch 7048/10000, Train Loss: 1.0750, Train Accuracy: 0.8426, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7049/10000, Train Loss: 1.0911, Train Accuracy: 0.8170, Val Loss: 1.1853, Val Accuracy: 0.7188 Epoch 7050/10000, Train Loss: 1.0852, Train Accuracy: 0.8281, Val Loss: 1.1853, Val Accuracy: 0.7188 Epoch 7051/10000, Train Loss: 1.0820, Train Accuracy: 0.8281, Val Loss: 1.1856, Val Accuracy: 0.7188 Epoch 7052/10000, Train Loss: 1.0906, Train Accuracy: 0.8203, Val Loss: 1.1857, Val Accuracy: 0.7188 Epoch 7053/10000, Train Loss: 1.0900, Train Accuracy: 0.8237, Val Loss: 1.1856, Val Accuracy: 0.7188 Epoch 7054/10000, Train Loss: 1.0893, Train Accuracy: 0.8270, Val Loss: 1.1854, Val Accuracy: 0.7232 Epoch 7055/10000, Train Loss: 1.0836, Train Accuracy: 0.8348, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7056/10000, Train Loss: 1.0837, Train Accuracy: 0.8337, Val Loss: 1.1852, Val Accuracy: 0.7188 Epoch 7057/10000, Train Loss: 1.0867, Train Accuracy: 0.8237, Val Loss: 1.1857, Val Accuracy: 0.7188 Epoch 7058/10000, Train Loss: 1.0696, Train Accuracy: 0.8449, Val Loss: 1.1858, Val Accuracy: 0.7232 Epoch 7059/10000, Train Loss: 1.0899, Train Accuracy: 0.8203, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 7060/10000, Train Loss: 1.0784, Train Accuracy: 0.8337, Val Loss: 1.1858, Val Accuracy: 0.7232 Epoch 7061/10000, Train Loss: 1.0691, Train Accuracy: 0.8438, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 7062/10000, Train Loss: 1.0911, Train Accuracy: 0.8237, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 7063/10000, Train Loss: 1.0799, Train Accuracy: 0.8304, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 7064/10000, Train Loss: 1.0806, Train Accuracy: 0.8404, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 7065/10000, Train Loss: 1.0833, Train Accuracy: 0.8214, Val Loss: 1.1858, Val Accuracy: 0.7232 Epoch 7066/10000, Train Loss: 1.0972, Train Accuracy: 0.8203, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 7067/10000, Train Loss: 1.0949, Train Accuracy: 0.8225, Val Loss: 1.1861, Val Accuracy: 0.7188 Epoch 7068/10000, Train Loss: 1.0941, Train Accuracy: 0.8237, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 7069/10000, Train Loss: 1.0976, Train Accuracy: 0.8147, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 7070/10000, Train Loss: 1.1119, Train Accuracy: 0.8002, Val Loss: 1.1860, Val Accuracy: 0.7188 Epoch 7071/10000, Train Loss: 1.0801, Train Accuracy: 0.8326, Val Loss: 1.1857, Val Accuracy: 0.7188 Epoch 7072/10000, Train Loss: 1.0858, Train Accuracy: 0.8237, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7073/10000, Train Loss: 1.0731, Train Accuracy: 0.8460, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7074/10000, Train Loss: 1.0876, Train Accuracy: 0.8259, Val Loss: 1.1855, Val Accuracy: 0.7188 Epoch 7075/10000, Train Loss: 1.0767, Train Accuracy: 0.8415, Val Loss: 1.1856, Val Accuracy: 0.7188 Epoch 7076/10000, Train Loss: 1.0895, Train Accuracy: 0.8214, Val Loss: 1.1857, Val Accuracy: 0.7188 Epoch 7077/10000, Train Loss: 1.0901, Train Accuracy: 0.8203, Val Loss: 1.1853, Val Accuracy: 0.7188 Epoch 7078/10000, Train Loss: 1.0932, Train Accuracy: 0.8192, Val Loss: 1.1856, Val Accuracy: 0.7188 Epoch 7079/10000, Train Loss: 1.0752, Train Accuracy: 0.8393, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 7080/10000, Train Loss: 1.1000, Train Accuracy: 0.8103, Val Loss: 1.1858, Val Accuracy: 0.7188 Epoch 7081/10000, Train Loss: 1.0832, Train Accuracy: 0.8337, Val Loss: 1.1861, Val Accuracy: 0.7232 Epoch 7082/10000, Train Loss: 1.0744, Train Accuracy: 0.8348, Val Loss: 1.1858, Val Accuracy: 0.7188 Epoch 7083/10000, Train Loss: 1.0695, Train Accuracy: 0.8493, Val Loss: 1.1858, Val Accuracy: 0.7188 Epoch 7084/10000, Train Loss: 1.0939, Train Accuracy: 0.8181, Val Loss: 1.1857, Val Accuracy: 0.7188 Epoch 7085/10000, Train Loss: 1.0883, Train Accuracy: 0.8225, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 7086/10000, Train Loss: 1.0817, Train Accuracy: 0.8281, Val Loss: 1.1860, Val Accuracy: 0.7277 Epoch 7087/10000, Train Loss: 1.0830, Train Accuracy: 0.8292, Val Loss: 1.1859, Val Accuracy: 0.7277 Epoch 7088/10000, Train Loss: 1.0964, Train Accuracy: 0.8170, Val Loss: 1.1858, Val Accuracy: 0.7232 Epoch 7089/10000, Train Loss: 1.0873, Train Accuracy: 0.8292, Val Loss: 1.1860, Val Accuracy: 0.7232 Epoch 7090/10000, Train Loss: 1.0875, Train Accuracy: 0.8292, Val Loss: 1.1859, Val Accuracy: 0.7232 Epoch 7091/10000, Train Loss: 1.0980, Train Accuracy: 0.8170, Val Loss: 1.1860, Val Accuracy: 0.7232 Epoch 7092/10000, Train Loss: 1.0778, Train Accuracy: 0.8415, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 7093/10000, Train Loss: 1.0900, Train Accuracy: 0.8259, Val Loss: 1.1858, Val Accuracy: 0.7232 Epoch 7094/10000, Train Loss: 1.0730, Train Accuracy: 0.8426, Val Loss: 1.1857, Val Accuracy: 0.7232 Epoch 7095/10000, Train Loss: 1.0771, Train Accuracy: 0.8359, Val Loss: 1.1854, Val Accuracy: 0.7232 Epoch 7096/10000, Train Loss: 1.0850, Train Accuracy: 0.8225, Val Loss: 1.1856, Val Accuracy: 0.7277 Epoch 7097/10000, Train Loss: 1.0842, Train Accuracy: 0.8315, Val Loss: 1.1855, Val Accuracy: 0.7232 Epoch 7098/10000, Train Loss: 1.0765, Train Accuracy: 0.8404, Val Loss: 1.1851, Val Accuracy: 0.7232 Epoch 7099/10000, Train Loss: 1.0880, Train Accuracy: 0.8248, Val Loss: 1.1853, Val Accuracy: 0.7277 Epoch 7100/10000, Train Loss: 1.0729, Train Accuracy: 0.8426, Val Loss: 1.1851, Val Accuracy: 0.7321 Epoch 7101/10000, Train Loss: 1.0824, Train Accuracy: 0.8237, Val Loss: 1.1850, Val Accuracy: 0.7321 Epoch 7102/10000, Train Loss: 1.0811, Train Accuracy: 0.8359, Val Loss: 1.1850, Val Accuracy: 0.7277 Epoch 7103/10000, Train Loss: 1.0742, Train Accuracy: 0.8404, Val Loss: 1.1851, Val Accuracy: 0.7321 Epoch 7104/10000, Train Loss: 1.0671, Train Accuracy: 0.8516, Val Loss: 1.1853, Val Accuracy: 0.7321 Epoch 7105/10000, Train Loss: 1.0974, Train Accuracy: 0.8125, Val Loss: 1.1854, Val Accuracy: 0.7277 Epoch 7106/10000, Train Loss: 1.0889, Train Accuracy: 0.8259, Val Loss: 1.1857, Val Accuracy: 0.7277 Epoch 7107/10000, Train Loss: 1.0844, Train Accuracy: 0.8292, Val Loss: 1.1856, Val Accuracy: 0.7277 Epoch 7108/10000, Train Loss: 1.0780, Train Accuracy: 0.8326, Val Loss: 1.1853, Val Accuracy: 0.7277 Epoch 7109/10000, Train Loss: 1.0832, Train Accuracy: 0.8348, Val Loss: 1.1850, Val Accuracy: 0.7232 Epoch 7110/10000, Train Loss: 1.0781, Train Accuracy: 0.8382, Val Loss: 1.1848, Val Accuracy: 0.7232 Epoch 7111/10000, Train Loss: 1.0829, Train Accuracy: 0.8270, Val Loss: 1.1847, Val Accuracy: 0.7277 Epoch 7112/10000, Train Loss: 1.0770, Train Accuracy: 0.8382, Val Loss: 1.1843, Val Accuracy: 0.7321 Epoch 7113/10000, Train Loss: 1.1030, Train Accuracy: 0.8103, Val Loss: 1.1844, Val Accuracy: 0.7321 Epoch 7114/10000, Train Loss: 1.0746, Train Accuracy: 0.8404, Val Loss: 1.1845, Val Accuracy: 0.7277 Epoch 7115/10000, Train Loss: 1.0701, Train Accuracy: 0.8371, Val Loss: 1.1841, Val Accuracy: 0.7277 Epoch 7116/10000, Train Loss: 1.0871, Train Accuracy: 0.8237, Val Loss: 1.1844, Val Accuracy: 0.7277 Epoch 7117/10000, Train Loss: 1.0896, Train Accuracy: 0.8237, Val Loss: 1.1842, Val Accuracy: 0.7232 Epoch 7118/10000, Train Loss: 1.0794, Train Accuracy: 0.8382, Val Loss: 1.1842, Val Accuracy: 0.7277 Epoch 7119/10000, Train Loss: 1.0896, Train Accuracy: 0.8237, Val Loss: 1.1842, Val Accuracy: 0.7232 Epoch 7120/10000, Train Loss: 1.0842, Train Accuracy: 0.8315, Val Loss: 1.1844, Val Accuracy: 0.7232 Epoch 7121/10000, Train Loss: 1.0969, Train Accuracy: 0.8136, Val Loss: 1.1844, Val Accuracy: 0.7232 Epoch 7122/10000, Train Loss: 1.0779, Train Accuracy: 0.8359, Val Loss: 1.1842, Val Accuracy: 0.7277 Epoch 7123/10000, Train Loss: 1.0720, Train Accuracy: 0.8493, Val Loss: 1.1845, Val Accuracy: 0.7277 Epoch 7124/10000, Train Loss: 1.0843, Train Accuracy: 0.8371, Val Loss: 1.1846, Val Accuracy: 0.7321 Epoch 7125/10000, Train Loss: 1.0742, Train Accuracy: 0.8371, Val Loss: 1.1847, Val Accuracy: 0.7277 Epoch 7126/10000, Train Loss: 1.0867, Train Accuracy: 0.8270, Val Loss: 1.1847, Val Accuracy: 0.7277 Epoch 7127/10000, Train Loss: 1.0849, Train Accuracy: 0.8270, Val Loss: 1.1846, Val Accuracy: 0.7277 Epoch 7128/10000, Train Loss: 1.0842, Train Accuracy: 0.8248, Val Loss: 1.1845, Val Accuracy: 0.7321 Epoch 7129/10000, Train Loss: 1.0954, Train Accuracy: 0.8192, Val Loss: 1.1846, Val Accuracy: 0.7321 Epoch 7130/10000, Train Loss: 1.0902, Train Accuracy: 0.8203, Val Loss: 1.1845, Val Accuracy: 0.7321 Epoch 7131/10000, Train Loss: 1.0888, Train Accuracy: 0.8158, Val Loss: 1.1845, Val Accuracy: 0.7321 Epoch 7132/10000, Train Loss: 1.0846, Train Accuracy: 0.8259, Val Loss: 1.1847, Val Accuracy: 0.7321 Epoch 7133/10000, Train Loss: 1.0843, Train Accuracy: 0.8304, Val Loss: 1.1844, Val Accuracy: 0.7321 Epoch 7134/10000, Train Loss: 1.0842, Train Accuracy: 0.8270, Val Loss: 1.1845, Val Accuracy: 0.7321 Epoch 7135/10000, Train Loss: 1.0787, Train Accuracy: 0.8292, Val Loss: 1.1842, Val Accuracy: 0.7321 Epoch 7136/10000, Train Loss: 1.0914, Train Accuracy: 0.8248, Val Loss: 1.1841, Val Accuracy: 0.7321 Epoch 7137/10000, Train Loss: 1.0913, Train Accuracy: 0.8147, Val Loss: 1.1842, Val Accuracy: 0.7277 Epoch 7138/10000, Train Loss: 1.0841, Train Accuracy: 0.8393, Val Loss: 1.1841, Val Accuracy: 0.7321 Epoch 7139/10000, Train Loss: 1.0928, Train Accuracy: 0.8192, Val Loss: 1.1838, Val Accuracy: 0.7366 Epoch 7140/10000, Train Loss: 1.0860, Train Accuracy: 0.8259, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7141/10000, Train Loss: 1.0925, Train Accuracy: 0.8103, Val Loss: 1.1837, Val Accuracy: 0.7321 Epoch 7142/10000, Train Loss: 1.0801, Train Accuracy: 0.8326, Val Loss: 1.1838, Val Accuracy: 0.7321 Epoch 7143/10000, Train Loss: 1.0883, Train Accuracy: 0.8270, Val Loss: 1.1837, Val Accuracy: 0.7277 Epoch 7144/10000, Train Loss: 1.0945, Train Accuracy: 0.8170, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7145/10000, Train Loss: 1.0928, Train Accuracy: 0.8203, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7146/10000, Train Loss: 1.0936, Train Accuracy: 0.8181, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7147/10000, Train Loss: 1.0849, Train Accuracy: 0.8270, Val Loss: 1.1836, Val Accuracy: 0.7321 Epoch 7148/10000, Train Loss: 1.0831, Train Accuracy: 0.8326, Val Loss: 1.1837, Val Accuracy: 0.7321 Epoch 7149/10000, Train Loss: 1.0808, Train Accuracy: 0.8438, Val Loss: 1.1838, Val Accuracy: 0.7321 Epoch 7150/10000, Train Loss: 1.0825, Train Accuracy: 0.8382, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7151/10000, Train Loss: 1.0913, Train Accuracy: 0.8259, Val Loss: 1.1833, Val Accuracy: 0.7321 Epoch 7152/10000, Train Loss: 1.0866, Train Accuracy: 0.8270, Val Loss: 1.1835, Val Accuracy: 0.7321 Epoch 7153/10000, Train Loss: 1.0661, Train Accuracy: 0.8493, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7154/10000, Train Loss: 1.0781, Train Accuracy: 0.8326, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7155/10000, Train Loss: 1.0775, Train Accuracy: 0.8393, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7156/10000, Train Loss: 1.0938, Train Accuracy: 0.8181, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7157/10000, Train Loss: 1.1017, Train Accuracy: 0.8047, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7158/10000, Train Loss: 1.0812, Train Accuracy: 0.8337, Val Loss: 1.1835, Val Accuracy: 0.7321 Epoch 7159/10000, Train Loss: 1.0677, Train Accuracy: 0.8449, Val Loss: 1.1837, Val Accuracy: 0.7321 Epoch 7160/10000, Train Loss: 1.0822, Train Accuracy: 0.8326, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7161/10000, Train Loss: 1.0936, Train Accuracy: 0.8158, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7162/10000, Train Loss: 1.0918, Train Accuracy: 0.8214, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7163/10000, Train Loss: 1.0847, Train Accuracy: 0.8304, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7164/10000, Train Loss: 1.0820, Train Accuracy: 0.8359, Val Loss: 1.1835, Val Accuracy: 0.7321 Epoch 7165/10000, Train Loss: 1.0882, Train Accuracy: 0.8281, Val Loss: 1.1832, Val Accuracy: 0.7321 Epoch 7166/10000, Train Loss: 1.0814, Train Accuracy: 0.8248, Val Loss: 1.1831, Val Accuracy: 0.7321 Epoch 7167/10000, Train Loss: 1.0837, Train Accuracy: 0.8326, Val Loss: 1.1830, Val Accuracy: 0.7321 Epoch 7168/10000, Train Loss: 1.0863, Train Accuracy: 0.8281, Val Loss: 1.1828, Val Accuracy: 0.7321 Epoch 7169/10000, Train Loss: 1.0916, Train Accuracy: 0.8237, Val Loss: 1.1827, Val Accuracy: 0.7366 Epoch 7170/10000, Train Loss: 1.0855, Train Accuracy: 0.8281, Val Loss: 1.1829, Val Accuracy: 0.7366 Epoch 7171/10000, Train Loss: 1.0803, Train Accuracy: 0.8281, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7172/10000, Train Loss: 1.0757, Train Accuracy: 0.8393, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7173/10000, Train Loss: 1.0848, Train Accuracy: 0.8248, Val Loss: 1.1828, Val Accuracy: 0.7321 Epoch 7174/10000, Train Loss: 1.0845, Train Accuracy: 0.8214, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7175/10000, Train Loss: 1.0821, Train Accuracy: 0.8259, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7176/10000, Train Loss: 1.0716, Train Accuracy: 0.8382, Val Loss: 1.1830, Val Accuracy: 0.7321 Epoch 7177/10000, Train Loss: 1.0782, Train Accuracy: 0.8371, Val Loss: 1.1831, Val Accuracy: 0.7366 Epoch 7178/10000, Train Loss: 1.0887, Train Accuracy: 0.8203, Val Loss: 1.1830, Val Accuracy: 0.7366 Epoch 7179/10000, Train Loss: 1.0788, Train Accuracy: 0.8315, Val Loss: 1.1830, Val Accuracy: 0.7366 Epoch 7180/10000, Train Loss: 1.0890, Train Accuracy: 0.8181, Val Loss: 1.1833, Val Accuracy: 0.7366 Epoch 7181/10000, Train Loss: 1.0724, Train Accuracy: 0.8471, Val Loss: 1.1834, Val Accuracy: 0.7366 Epoch 7182/10000, Train Loss: 1.0795, Train Accuracy: 0.8371, Val Loss: 1.1832, Val Accuracy: 0.7366 Epoch 7183/10000, Train Loss: 1.0803, Train Accuracy: 0.8326, Val Loss: 1.1828, Val Accuracy: 0.7366 Epoch 7184/10000, Train Loss: 1.0903, Train Accuracy: 0.8237, Val Loss: 1.1823, Val Accuracy: 0.7366 Epoch 7185/10000, Train Loss: 1.0814, Train Accuracy: 0.8259, Val Loss: 1.1825, Val Accuracy: 0.7366 Epoch 7186/10000, Train Loss: 1.0858, Train Accuracy: 0.8270, Val Loss: 1.1824, Val Accuracy: 0.7366 Epoch 7187/10000, Train Loss: 1.0750, Train Accuracy: 0.8382, Val Loss: 1.1824, Val Accuracy: 0.7366 Epoch 7188/10000, Train Loss: 1.0767, Train Accuracy: 0.8415, Val Loss: 1.1825, Val Accuracy: 0.7366 Epoch 7189/10000, Train Loss: 1.0844, Train Accuracy: 0.8281, Val Loss: 1.1826, Val Accuracy: 0.7366 Epoch 7190/10000, Train Loss: 1.0838, Train Accuracy: 0.8259, Val Loss: 1.1825, Val Accuracy: 0.7366 Epoch 7191/10000, Train Loss: 1.0797, Train Accuracy: 0.8304, Val Loss: 1.1828, Val Accuracy: 0.7321 Epoch 7192/10000, Train Loss: 1.0904, Train Accuracy: 0.8237, Val Loss: 1.1826, Val Accuracy: 0.7366 Epoch 7193/10000, Train Loss: 1.0699, Train Accuracy: 0.8460, Val Loss: 1.1827, Val Accuracy: 0.7366 Epoch 7194/10000, Train Loss: 1.0743, Train Accuracy: 0.8393, Val Loss: 1.1825, Val Accuracy: 0.7366 Epoch 7195/10000, Train Loss: 1.0876, Train Accuracy: 0.8248, Val Loss: 1.1824, Val Accuracy: 0.7366 Epoch 7196/10000, Train Loss: 1.0847, Train Accuracy: 0.8326, Val Loss: 1.1826, Val Accuracy: 0.7366 Epoch 7197/10000, Train Loss: 1.0879, Train Accuracy: 0.8270, Val Loss: 1.1827, Val Accuracy: 0.7366 Epoch 7198/10000, Train Loss: 1.0873, Train Accuracy: 0.8237, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7199/10000, Train Loss: 1.0683, Train Accuracy: 0.8460, Val Loss: 1.1825, Val Accuracy: 0.7321 Epoch 7200/10000, Train Loss: 1.0768, Train Accuracy: 0.8393, Val Loss: 1.1825, Val Accuracy: 0.7321 Epoch 7201/10000, Train Loss: 1.0683, Train Accuracy: 0.8516, Val Loss: 1.1822, Val Accuracy: 0.7321 Epoch 7202/10000, Train Loss: 1.0823, Train Accuracy: 0.8304, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7203/10000, Train Loss: 1.0992, Train Accuracy: 0.8080, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7204/10000, Train Loss: 1.0848, Train Accuracy: 0.8326, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7205/10000, Train Loss: 1.0767, Train Accuracy: 0.8404, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7206/10000, Train Loss: 1.0763, Train Accuracy: 0.8337, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7207/10000, Train Loss: 1.0802, Train Accuracy: 0.8359, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7208/10000, Train Loss: 1.0840, Train Accuracy: 0.8270, Val Loss: 1.1818, Val Accuracy: 0.7321 Epoch 7209/10000, Train Loss: 1.0824, Train Accuracy: 0.8270, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7210/10000, Train Loss: 1.0776, Train Accuracy: 0.8426, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7211/10000, Train Loss: 1.0832, Train Accuracy: 0.8225, Val Loss: 1.1822, Val Accuracy: 0.7321 Epoch 7212/10000, Train Loss: 1.0747, Train Accuracy: 0.8482, Val Loss: 1.1823, Val Accuracy: 0.7321 Epoch 7213/10000, Train Loss: 1.0805, Train Accuracy: 0.8259, Val Loss: 1.1823, Val Accuracy: 0.7321 Epoch 7214/10000, Train Loss: 1.0860, Train Accuracy: 0.8248, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7215/10000, Train Loss: 1.0822, Train Accuracy: 0.8292, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7216/10000, Train Loss: 1.0726, Train Accuracy: 0.8382, Val Loss: 1.1826, Val Accuracy: 0.7366 Epoch 7217/10000, Train Loss: 1.0881, Train Accuracy: 0.8214, Val Loss: 1.1826, Val Accuracy: 0.7366 Epoch 7218/10000, Train Loss: 1.0856, Train Accuracy: 0.8304, Val Loss: 1.1825, Val Accuracy: 0.7366 Epoch 7219/10000, Train Loss: 1.0685, Train Accuracy: 0.8404, Val Loss: 1.1827, Val Accuracy: 0.7366 Epoch 7220/10000, Train Loss: 1.0801, Train Accuracy: 0.8326, Val Loss: 1.1826, Val Accuracy: 0.7321 Epoch 7221/10000, Train Loss: 1.0836, Train Accuracy: 0.8337, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7222/10000, Train Loss: 1.0937, Train Accuracy: 0.8147, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7223/10000, Train Loss: 1.0723, Train Accuracy: 0.8393, Val Loss: 1.1828, Val Accuracy: 0.7321 Epoch 7224/10000, Train Loss: 1.0742, Train Accuracy: 0.8382, Val Loss: 1.1824, Val Accuracy: 0.7321 Epoch 7225/10000, Train Loss: 1.0839, Train Accuracy: 0.8225, Val Loss: 1.1824, Val Accuracy: 0.7321 Epoch 7226/10000, Train Loss: 1.0890, Train Accuracy: 0.8248, Val Loss: 1.1822, Val Accuracy: 0.7321 Epoch 7227/10000, Train Loss: 1.0861, Train Accuracy: 0.8304, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7228/10000, Train Loss: 1.0851, Train Accuracy: 0.8371, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7229/10000, Train Loss: 1.0843, Train Accuracy: 0.8281, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7230/10000, Train Loss: 1.0808, Train Accuracy: 0.8426, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7231/10000, Train Loss: 1.0940, Train Accuracy: 0.8237, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7232/10000, Train Loss: 1.0870, Train Accuracy: 0.8270, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7233/10000, Train Loss: 1.0773, Train Accuracy: 0.8337, Val Loss: 1.1822, Val Accuracy: 0.7366 Epoch 7234/10000, Train Loss: 1.0638, Train Accuracy: 0.8516, Val Loss: 1.1819, Val Accuracy: 0.7366 Epoch 7235/10000, Train Loss: 1.0778, Train Accuracy: 0.8382, Val Loss: 1.1819, Val Accuracy: 0.7366 Epoch 7236/10000, Train Loss: 1.0769, Train Accuracy: 0.8337, Val Loss: 1.1820, Val Accuracy: 0.7366 Epoch 7237/10000, Train Loss: 1.0855, Train Accuracy: 0.8281, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7238/10000, Train Loss: 1.0873, Train Accuracy: 0.8304, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7239/10000, Train Loss: 1.0822, Train Accuracy: 0.8304, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7240/10000, Train Loss: 1.0719, Train Accuracy: 0.8382, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7241/10000, Train Loss: 1.0789, Train Accuracy: 0.8393, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7242/10000, Train Loss: 1.0817, Train Accuracy: 0.8315, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7243/10000, Train Loss: 1.0799, Train Accuracy: 0.8326, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7244/10000, Train Loss: 1.0966, Train Accuracy: 0.8136, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7245/10000, Train Loss: 1.0780, Train Accuracy: 0.8304, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7246/10000, Train Loss: 1.0769, Train Accuracy: 0.8359, Val Loss: 1.1818, Val Accuracy: 0.7321 Epoch 7247/10000, Train Loss: 1.0828, Train Accuracy: 0.8292, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7248/10000, Train Loss: 1.0841, Train Accuracy: 0.8292, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7249/10000, Train Loss: 1.0756, Train Accuracy: 0.8438, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7250/10000, Train Loss: 1.0714, Train Accuracy: 0.8504, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7251/10000, Train Loss: 1.0805, Train Accuracy: 0.8371, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7252/10000, Train Loss: 1.0903, Train Accuracy: 0.8203, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7253/10000, Train Loss: 1.0898, Train Accuracy: 0.8270, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7254/10000, Train Loss: 1.0715, Train Accuracy: 0.8415, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7255/10000, Train Loss: 1.0616, Train Accuracy: 0.8516, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7256/10000, Train Loss: 1.0834, Train Accuracy: 0.8281, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7257/10000, Train Loss: 1.0935, Train Accuracy: 0.8192, Val Loss: 1.1829, Val Accuracy: 0.7232 Epoch 7258/10000, Train Loss: 1.0909, Train Accuracy: 0.8225, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7259/10000, Train Loss: 1.0949, Train Accuracy: 0.8147, Val Loss: 1.1826, Val Accuracy: 0.7321 Epoch 7260/10000, Train Loss: 1.0769, Train Accuracy: 0.8393, Val Loss: 1.1824, Val Accuracy: 0.7321 Epoch 7261/10000, Train Loss: 1.0744, Train Accuracy: 0.8471, Val Loss: 1.1825, Val Accuracy: 0.7321 Epoch 7262/10000, Train Loss: 1.0829, Train Accuracy: 0.8359, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7263/10000, Train Loss: 1.0785, Train Accuracy: 0.8371, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7264/10000, Train Loss: 1.0801, Train Accuracy: 0.8348, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7265/10000, Train Loss: 1.0872, Train Accuracy: 0.8192, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7266/10000, Train Loss: 1.0770, Train Accuracy: 0.8371, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7267/10000, Train Loss: 1.0803, Train Accuracy: 0.8393, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7268/10000, Train Loss: 1.0900, Train Accuracy: 0.8181, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7269/10000, Train Loss: 1.0762, Train Accuracy: 0.8404, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7270/10000, Train Loss: 1.0788, Train Accuracy: 0.8382, Val Loss: 1.1832, Val Accuracy: 0.7321 Epoch 7271/10000, Train Loss: 1.0823, Train Accuracy: 0.8348, Val Loss: 1.1830, Val Accuracy: 0.7321 Epoch 7272/10000, Train Loss: 1.0786, Train Accuracy: 0.8393, Val Loss: 1.1832, Val Accuracy: 0.7321 Epoch 7273/10000, Train Loss: 1.0892, Train Accuracy: 0.8281, Val Loss: 1.1831, Val Accuracy: 0.7321 Epoch 7274/10000, Train Loss: 1.0743, Train Accuracy: 0.8371, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7275/10000, Train Loss: 1.0829, Train Accuracy: 0.8315, Val Loss: 1.1832, Val Accuracy: 0.7232 Epoch 7276/10000, Train Loss: 1.0783, Train Accuracy: 0.8382, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7277/10000, Train Loss: 1.0820, Train Accuracy: 0.8315, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7278/10000, Train Loss: 1.0666, Train Accuracy: 0.8493, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7279/10000, Train Loss: 1.0864, Train Accuracy: 0.8248, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7280/10000, Train Loss: 1.0834, Train Accuracy: 0.8281, Val Loss: 1.1838, Val Accuracy: 0.7232 Epoch 7281/10000, Train Loss: 1.0743, Train Accuracy: 0.8449, Val Loss: 1.1839, Val Accuracy: 0.7188 Epoch 7282/10000, Train Loss: 1.0836, Train Accuracy: 0.8270, Val Loss: 1.1841, Val Accuracy: 0.7232 Epoch 7283/10000, Train Loss: 1.0919, Train Accuracy: 0.8170, Val Loss: 1.1840, Val Accuracy: 0.7232 Epoch 7284/10000, Train Loss: 1.0790, Train Accuracy: 0.8359, Val Loss: 1.1841, Val Accuracy: 0.7232 Epoch 7285/10000, Train Loss: 1.0776, Train Accuracy: 0.8404, Val Loss: 1.1840, Val Accuracy: 0.7188 Epoch 7286/10000, Train Loss: 1.0841, Train Accuracy: 0.8359, Val Loss: 1.1838, Val Accuracy: 0.7232 Epoch 7287/10000, Train Loss: 1.0805, Train Accuracy: 0.8259, Val Loss: 1.1838, Val Accuracy: 0.7188 Epoch 7288/10000, Train Loss: 1.0689, Train Accuracy: 0.8438, Val Loss: 1.1835, Val Accuracy: 0.7232 Epoch 7289/10000, Train Loss: 1.0731, Train Accuracy: 0.8371, Val Loss: 1.1835, Val Accuracy: 0.7232 Epoch 7290/10000, Train Loss: 1.0733, Train Accuracy: 0.8382, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7291/10000, Train Loss: 1.0769, Train Accuracy: 0.8415, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7292/10000, Train Loss: 1.0804, Train Accuracy: 0.8292, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7293/10000, Train Loss: 1.0683, Train Accuracy: 0.8504, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7294/10000, Train Loss: 1.0800, Train Accuracy: 0.8292, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7295/10000, Train Loss: 1.0815, Train Accuracy: 0.8315, Val Loss: 1.1834, Val Accuracy: 0.7232 Epoch 7296/10000, Train Loss: 1.0761, Train Accuracy: 0.8382, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7297/10000, Train Loss: 1.0821, Train Accuracy: 0.8259, Val Loss: 1.1833, Val Accuracy: 0.7188 Epoch 7298/10000, Train Loss: 1.0808, Train Accuracy: 0.8237, Val Loss: 1.1834, Val Accuracy: 0.7188 Epoch 7299/10000, Train Loss: 1.0848, Train Accuracy: 0.8259, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7300/10000, Train Loss: 1.0807, Train Accuracy: 0.8315, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7301/10000, Train Loss: 1.0884, Train Accuracy: 0.8203, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7302/10000, Train Loss: 1.0807, Train Accuracy: 0.8315, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7303/10000, Train Loss: 1.0767, Train Accuracy: 0.8348, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7304/10000, Train Loss: 1.0854, Train Accuracy: 0.8270, Val Loss: 1.1839, Val Accuracy: 0.7277 Epoch 7305/10000, Train Loss: 1.0735, Train Accuracy: 0.8471, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7306/10000, Train Loss: 1.0749, Train Accuracy: 0.8415, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7307/10000, Train Loss: 1.0796, Train Accuracy: 0.8371, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7308/10000, Train Loss: 1.0725, Train Accuracy: 0.8426, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7309/10000, Train Loss: 1.0836, Train Accuracy: 0.8359, Val Loss: 1.1839, Val Accuracy: 0.7277 Epoch 7310/10000, Train Loss: 1.0774, Train Accuracy: 0.8337, Val Loss: 1.1841, Val Accuracy: 0.7277 Epoch 7311/10000, Train Loss: 1.0778, Train Accuracy: 0.8348, Val Loss: 1.1844, Val Accuracy: 0.7277 Epoch 7312/10000, Train Loss: 1.0857, Train Accuracy: 0.8248, Val Loss: 1.1845, Val Accuracy: 0.7277 Epoch 7313/10000, Train Loss: 1.0818, Train Accuracy: 0.8337, Val Loss: 1.1848, Val Accuracy: 0.7277 Epoch 7314/10000, Train Loss: 1.0745, Train Accuracy: 0.8371, Val Loss: 1.1845, Val Accuracy: 0.7277 Epoch 7315/10000, Train Loss: 1.0783, Train Accuracy: 0.8348, Val Loss: 1.1847, Val Accuracy: 0.7232 Epoch 7316/10000, Train Loss: 1.0805, Train Accuracy: 0.8315, Val Loss: 1.1842, Val Accuracy: 0.7277 Epoch 7317/10000, Train Loss: 1.0988, Train Accuracy: 0.8058, Val Loss: 1.1839, Val Accuracy: 0.7277 Epoch 7318/10000, Train Loss: 1.0772, Train Accuracy: 0.8348, Val Loss: 1.1840, Val Accuracy: 0.7277 Epoch 7319/10000, Train Loss: 1.0768, Train Accuracy: 0.8393, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7320/10000, Train Loss: 1.0862, Train Accuracy: 0.8147, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7321/10000, Train Loss: 1.0738, Train Accuracy: 0.8415, Val Loss: 1.1837, Val Accuracy: 0.7277 Epoch 7322/10000, Train Loss: 1.0811, Train Accuracy: 0.8337, Val Loss: 1.1840, Val Accuracy: 0.7277 Epoch 7323/10000, Train Loss: 1.0717, Train Accuracy: 0.8315, Val Loss: 1.1842, Val Accuracy: 0.7277 Epoch 7324/10000, Train Loss: 1.0697, Train Accuracy: 0.8382, Val Loss: 1.1840, Val Accuracy: 0.7277 Epoch 7325/10000, Train Loss: 1.0782, Train Accuracy: 0.8359, Val Loss: 1.1837, Val Accuracy: 0.7277 Epoch 7326/10000, Train Loss: 1.0835, Train Accuracy: 0.8237, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7327/10000, Train Loss: 1.0805, Train Accuracy: 0.8292, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7328/10000, Train Loss: 1.0795, Train Accuracy: 0.8304, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7329/10000, Train Loss: 1.0646, Train Accuracy: 0.8538, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7330/10000, Train Loss: 1.0700, Train Accuracy: 0.8460, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7331/10000, Train Loss: 1.0741, Train Accuracy: 0.8382, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7332/10000, Train Loss: 1.0849, Train Accuracy: 0.8225, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7333/10000, Train Loss: 1.0767, Train Accuracy: 0.8382, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7334/10000, Train Loss: 1.0747, Train Accuracy: 0.8359, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7335/10000, Train Loss: 1.0700, Train Accuracy: 0.8426, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7336/10000, Train Loss: 1.0888, Train Accuracy: 0.8237, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7337/10000, Train Loss: 1.0784, Train Accuracy: 0.8348, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7338/10000, Train Loss: 1.0865, Train Accuracy: 0.8259, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7339/10000, Train Loss: 1.0806, Train Accuracy: 0.8304, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7340/10000, Train Loss: 1.0657, Train Accuracy: 0.8493, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7341/10000, Train Loss: 1.0793, Train Accuracy: 0.8382, Val Loss: 1.1839, Val Accuracy: 0.7277 Epoch 7342/10000, Train Loss: 1.0724, Train Accuracy: 0.8404, Val Loss: 1.1840, Val Accuracy: 0.7277 Epoch 7343/10000, Train Loss: 1.0818, Train Accuracy: 0.8371, Val Loss: 1.1839, Val Accuracy: 0.7277 Epoch 7344/10000, Train Loss: 1.0761, Train Accuracy: 0.8371, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7345/10000, Train Loss: 1.0810, Train Accuracy: 0.8337, Val Loss: 1.1843, Val Accuracy: 0.7232 Epoch 7346/10000, Train Loss: 1.0732, Train Accuracy: 0.8460, Val Loss: 1.1839, Val Accuracy: 0.7232 Epoch 7347/10000, Train Loss: 1.0708, Train Accuracy: 0.8348, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7348/10000, Train Loss: 1.0721, Train Accuracy: 0.8471, Val Loss: 1.1837, Val Accuracy: 0.7232 Epoch 7349/10000, Train Loss: 1.0730, Train Accuracy: 0.8404, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7350/10000, Train Loss: 1.0803, Train Accuracy: 0.8315, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7351/10000, Train Loss: 1.0789, Train Accuracy: 0.8348, Val Loss: 1.1832, Val Accuracy: 0.7232 Epoch 7352/10000, Train Loss: 1.0782, Train Accuracy: 0.8371, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7353/10000, Train Loss: 1.0751, Train Accuracy: 0.8348, Val Loss: 1.1832, Val Accuracy: 0.7232 Epoch 7354/10000, Train Loss: 1.0743, Train Accuracy: 0.8359, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7355/10000, Train Loss: 1.0735, Train Accuracy: 0.8449, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7356/10000, Train Loss: 1.0734, Train Accuracy: 0.8415, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7357/10000, Train Loss: 1.0884, Train Accuracy: 0.8248, Val Loss: 1.1832, Val Accuracy: 0.7366 Epoch 7358/10000, Train Loss: 1.0684, Train Accuracy: 0.8583, Val Loss: 1.1831, Val Accuracy: 0.7366 Epoch 7359/10000, Train Loss: 1.0775, Train Accuracy: 0.8326, Val Loss: 1.1833, Val Accuracy: 0.7321 Epoch 7360/10000, Train Loss: 1.0761, Train Accuracy: 0.8438, Val Loss: 1.1833, Val Accuracy: 0.7321 Epoch 7361/10000, Train Loss: 1.0767, Train Accuracy: 0.8315, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7362/10000, Train Loss: 1.0761, Train Accuracy: 0.8371, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7363/10000, Train Loss: 1.0725, Train Accuracy: 0.8393, Val Loss: 1.1831, Val Accuracy: 0.7321 Epoch 7364/10000, Train Loss: 1.0780, Train Accuracy: 0.8315, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7365/10000, Train Loss: 1.0828, Train Accuracy: 0.8270, Val Loss: 1.1837, Val Accuracy: 0.7277 Epoch 7366/10000, Train Loss: 1.0776, Train Accuracy: 0.8337, Val Loss: 1.1839, Val Accuracy: 0.7277 Epoch 7367/10000, Train Loss: 1.0787, Train Accuracy: 0.8348, Val Loss: 1.1838, Val Accuracy: 0.7277 Epoch 7368/10000, Train Loss: 1.0630, Train Accuracy: 0.8471, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7369/10000, Train Loss: 1.0670, Train Accuracy: 0.8493, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7370/10000, Train Loss: 1.0756, Train Accuracy: 0.8393, Val Loss: 1.1834, Val Accuracy: 0.7232 Epoch 7371/10000, Train Loss: 1.0759, Train Accuracy: 0.8404, Val Loss: 1.1834, Val Accuracy: 0.7232 Epoch 7372/10000, Train Loss: 1.0828, Train Accuracy: 0.8248, Val Loss: 1.1835, Val Accuracy: 0.7277 Epoch 7373/10000, Train Loss: 1.0727, Train Accuracy: 0.8471, Val Loss: 1.1836, Val Accuracy: 0.7188 Epoch 7374/10000, Train Loss: 1.0663, Train Accuracy: 0.8415, Val Loss: 1.1837, Val Accuracy: 0.7188 Epoch 7375/10000, Train Loss: 1.0799, Train Accuracy: 0.8326, Val Loss: 1.1836, Val Accuracy: 0.7188 Epoch 7376/10000, Train Loss: 1.0816, Train Accuracy: 0.8259, Val Loss: 1.1839, Val Accuracy: 0.7188 Epoch 7377/10000, Train Loss: 1.0765, Train Accuracy: 0.8348, Val Loss: 1.1837, Val Accuracy: 0.7188 Epoch 7378/10000, Train Loss: 1.0764, Train Accuracy: 0.8382, Val Loss: 1.1836, Val Accuracy: 0.7188 Epoch 7379/10000, Train Loss: 1.0877, Train Accuracy: 0.8192, Val Loss: 1.1835, Val Accuracy: 0.7188 Epoch 7380/10000, Train Loss: 1.0866, Train Accuracy: 0.8248, Val Loss: 1.1833, Val Accuracy: 0.7188 Epoch 7381/10000, Train Loss: 1.0874, Train Accuracy: 0.8281, Val Loss: 1.1835, Val Accuracy: 0.7188 Epoch 7382/10000, Train Loss: 1.0719, Train Accuracy: 0.8393, Val Loss: 1.1835, Val Accuracy: 0.7188 Epoch 7383/10000, Train Loss: 1.0795, Train Accuracy: 0.8304, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7384/10000, Train Loss: 1.0847, Train Accuracy: 0.8248, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7385/10000, Train Loss: 1.0839, Train Accuracy: 0.8248, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7386/10000, Train Loss: 1.0741, Train Accuracy: 0.8315, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7387/10000, Train Loss: 1.0893, Train Accuracy: 0.8203, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7388/10000, Train Loss: 1.0654, Train Accuracy: 0.8516, Val Loss: 1.1831, Val Accuracy: 0.7321 Epoch 7389/10000, Train Loss: 1.0737, Train Accuracy: 0.8449, Val Loss: 1.1830, Val Accuracy: 0.7321 Epoch 7390/10000, Train Loss: 1.0791, Train Accuracy: 0.8315, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7391/10000, Train Loss: 1.0774, Train Accuracy: 0.8371, Val Loss: 1.1831, Val Accuracy: 0.7321 Epoch 7392/10000, Train Loss: 1.0659, Train Accuracy: 0.8404, Val Loss: 1.1832, Val Accuracy: 0.7321 Epoch 7393/10000, Train Loss: 1.0654, Train Accuracy: 0.8471, Val Loss: 1.1831, Val Accuracy: 0.7321 Epoch 7394/10000, Train Loss: 1.0710, Train Accuracy: 0.8426, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7395/10000, Train Loss: 1.0748, Train Accuracy: 0.8359, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7396/10000, Train Loss: 1.0697, Train Accuracy: 0.8426, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7397/10000, Train Loss: 1.0764, Train Accuracy: 0.8359, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7398/10000, Train Loss: 1.0770, Train Accuracy: 0.8382, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7399/10000, Train Loss: 1.0641, Train Accuracy: 0.8538, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7400/10000, Train Loss: 1.0816, Train Accuracy: 0.8270, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7401/10000, Train Loss: 1.0876, Train Accuracy: 0.8214, Val Loss: 1.1832, Val Accuracy: 0.7232 Epoch 7402/10000, Train Loss: 1.0798, Train Accuracy: 0.8326, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7403/10000, Train Loss: 1.0804, Train Accuracy: 0.8326, Val Loss: 1.1830, Val Accuracy: 0.7188 Epoch 7404/10000, Train Loss: 1.0724, Train Accuracy: 0.8404, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7405/10000, Train Loss: 1.0707, Train Accuracy: 0.8482, Val Loss: 1.1833, Val Accuracy: 0.7188 Epoch 7406/10000, Train Loss: 1.0730, Train Accuracy: 0.8337, Val Loss: 1.1831, Val Accuracy: 0.7188 Epoch 7407/10000, Train Loss: 1.0780, Train Accuracy: 0.8304, Val Loss: 1.1828, Val Accuracy: 0.7188 Epoch 7408/10000, Train Loss: 1.0798, Train Accuracy: 0.8348, Val Loss: 1.1828, Val Accuracy: 0.7188 Epoch 7409/10000, Train Loss: 1.0807, Train Accuracy: 0.8326, Val Loss: 1.1827, Val Accuracy: 0.7232 Epoch 7410/10000, Train Loss: 1.0828, Train Accuracy: 0.8281, Val Loss: 1.1827, Val Accuracy: 0.7188 Epoch 7411/10000, Train Loss: 1.0799, Train Accuracy: 0.8348, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7412/10000, Train Loss: 1.0779, Train Accuracy: 0.8281, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7413/10000, Train Loss: 1.0764, Train Accuracy: 0.8348, Val Loss: 1.1829, Val Accuracy: 0.7232 Epoch 7414/10000, Train Loss: 1.0751, Train Accuracy: 0.8337, Val Loss: 1.1827, Val Accuracy: 0.7232 Epoch 7415/10000, Train Loss: 1.0560, Train Accuracy: 0.8583, Val Loss: 1.1825, Val Accuracy: 0.7321 Epoch 7416/10000, Train Loss: 1.0771, Train Accuracy: 0.8371, Val Loss: 1.1825, Val Accuracy: 0.7321 Epoch 7417/10000, Train Loss: 1.0738, Train Accuracy: 0.8337, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7418/10000, Train Loss: 1.0752, Train Accuracy: 0.8382, Val Loss: 1.1829, Val Accuracy: 0.7321 Epoch 7419/10000, Train Loss: 1.0798, Train Accuracy: 0.8315, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7420/10000, Train Loss: 1.0589, Train Accuracy: 0.8571, Val Loss: 1.1826, Val Accuracy: 0.7321 Epoch 7421/10000, Train Loss: 1.0827, Train Accuracy: 0.8315, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7422/10000, Train Loss: 1.0716, Train Accuracy: 0.8393, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7423/10000, Train Loss: 1.0613, Train Accuracy: 0.8538, Val Loss: 1.1830, Val Accuracy: 0.7321 Epoch 7424/10000, Train Loss: 1.0748, Train Accuracy: 0.8404, Val Loss: 1.1830, Val Accuracy: 0.7321 Epoch 7425/10000, Train Loss: 1.0747, Train Accuracy: 0.8393, Val Loss: 1.1826, Val Accuracy: 0.7321 Epoch 7426/10000, Train Loss: 1.0717, Train Accuracy: 0.8482, Val Loss: 1.1827, Val Accuracy: 0.7321 Epoch 7427/10000, Train Loss: 1.0623, Train Accuracy: 0.8583, Val Loss: 1.1825, Val Accuracy: 0.7321 Epoch 7428/10000, Train Loss: 1.0720, Train Accuracy: 0.8460, Val Loss: 1.1829, Val Accuracy: 0.7366 Epoch 7429/10000, Train Loss: 1.0823, Train Accuracy: 0.8348, Val Loss: 1.1831, Val Accuracy: 0.7277 Epoch 7430/10000, Train Loss: 1.0737, Train Accuracy: 0.8438, Val Loss: 1.1827, Val Accuracy: 0.7232 Epoch 7431/10000, Train Loss: 1.0875, Train Accuracy: 0.8281, Val Loss: 1.1830, Val Accuracy: 0.7232 Epoch 7432/10000, Train Loss: 1.0736, Train Accuracy: 0.8371, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7433/10000, Train Loss: 1.0812, Train Accuracy: 0.8281, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7434/10000, Train Loss: 1.0791, Train Accuracy: 0.8393, Val Loss: 1.1834, Val Accuracy: 0.7188 Epoch 7435/10000, Train Loss: 1.0821, Train Accuracy: 0.8281, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7436/10000, Train Loss: 1.0724, Train Accuracy: 0.8326, Val Loss: 1.1834, Val Accuracy: 0.7232 Epoch 7437/10000, Train Loss: 1.0679, Train Accuracy: 0.8482, Val Loss: 1.1836, Val Accuracy: 0.7277 Epoch 7438/10000, Train Loss: 1.0662, Train Accuracy: 0.8449, Val Loss: 1.1836, Val Accuracy: 0.7232 Epoch 7439/10000, Train Loss: 1.0771, Train Accuracy: 0.8359, Val Loss: 1.1834, Val Accuracy: 0.7321 Epoch 7440/10000, Train Loss: 1.0780, Train Accuracy: 0.8393, Val Loss: 1.1832, Val Accuracy: 0.7277 Epoch 7441/10000, Train Loss: 1.0701, Train Accuracy: 0.8471, Val Loss: 1.1833, Val Accuracy: 0.7277 Epoch 7442/10000, Train Loss: 1.0772, Train Accuracy: 0.8304, Val Loss: 1.1834, Val Accuracy: 0.7277 Epoch 7443/10000, Train Loss: 1.0809, Train Accuracy: 0.8348, Val Loss: 1.1835, Val Accuracy: 0.7232 Epoch 7444/10000, Train Loss: 1.0848, Train Accuracy: 0.8281, Val Loss: 1.1833, Val Accuracy: 0.7232 Epoch 7445/10000, Train Loss: 1.0728, Train Accuracy: 0.8404, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7446/10000, Train Loss: 1.0705, Train Accuracy: 0.8404, Val Loss: 1.1834, Val Accuracy: 0.7188 Epoch 7447/10000, Train Loss: 1.0596, Train Accuracy: 0.8571, Val Loss: 1.1835, Val Accuracy: 0.7143 Epoch 7448/10000, Train Loss: 1.0716, Train Accuracy: 0.8404, Val Loss: 1.1833, Val Accuracy: 0.7188 Epoch 7449/10000, Train Loss: 1.0894, Train Accuracy: 0.8158, Val Loss: 1.1833, Val Accuracy: 0.7188 Epoch 7450/10000, Train Loss: 1.0774, Train Accuracy: 0.8359, Val Loss: 1.1830, Val Accuracy: 0.7188 Epoch 7451/10000, Train Loss: 1.0750, Train Accuracy: 0.8393, Val Loss: 1.1831, Val Accuracy: 0.7232 Epoch 7452/10000, Train Loss: 1.0605, Train Accuracy: 0.8527, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7453/10000, Train Loss: 1.0809, Train Accuracy: 0.8270, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7454/10000, Train Loss: 1.0729, Train Accuracy: 0.8404, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7455/10000, Train Loss: 1.0716, Train Accuracy: 0.8460, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7456/10000, Train Loss: 1.0737, Train Accuracy: 0.8393, Val Loss: 1.1827, Val Accuracy: 0.7232 Epoch 7457/10000, Train Loss: 1.0769, Train Accuracy: 0.8337, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7458/10000, Train Loss: 1.0799, Train Accuracy: 0.8304, Val Loss: 1.1824, Val Accuracy: 0.7232 Epoch 7459/10000, Train Loss: 1.0744, Train Accuracy: 0.8449, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7460/10000, Train Loss: 1.0742, Train Accuracy: 0.8382, Val Loss: 1.1822, Val Accuracy: 0.7232 Epoch 7461/10000, Train Loss: 1.0675, Train Accuracy: 0.8449, Val Loss: 1.1824, Val Accuracy: 0.7232 Epoch 7462/10000, Train Loss: 1.0758, Train Accuracy: 0.8359, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7463/10000, Train Loss: 1.0763, Train Accuracy: 0.8315, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7464/10000, Train Loss: 1.0719, Train Accuracy: 0.8359, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7465/10000, Train Loss: 1.0585, Train Accuracy: 0.8516, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7466/10000, Train Loss: 1.0652, Train Accuracy: 0.8438, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7467/10000, Train Loss: 1.0626, Train Accuracy: 0.8538, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7468/10000, Train Loss: 1.0750, Train Accuracy: 0.8393, Val Loss: 1.1822, Val Accuracy: 0.7232 Epoch 7469/10000, Train Loss: 1.0691, Train Accuracy: 0.8482, Val Loss: 1.1819, Val Accuracy: 0.7321 Epoch 7470/10000, Train Loss: 1.0748, Train Accuracy: 0.8404, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7471/10000, Train Loss: 1.0853, Train Accuracy: 0.8281, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7472/10000, Train Loss: 1.0780, Train Accuracy: 0.8404, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7473/10000, Train Loss: 1.0710, Train Accuracy: 0.8382, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7474/10000, Train Loss: 1.0825, Train Accuracy: 0.8315, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7475/10000, Train Loss: 1.0735, Train Accuracy: 0.8415, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7476/10000, Train Loss: 1.0832, Train Accuracy: 0.8326, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7477/10000, Train Loss: 1.0663, Train Accuracy: 0.8426, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7478/10000, Train Loss: 1.0760, Train Accuracy: 0.8326, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7479/10000, Train Loss: 1.0776, Train Accuracy: 0.8315, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7480/10000, Train Loss: 1.0705, Train Accuracy: 0.8438, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7481/10000, Train Loss: 1.0707, Train Accuracy: 0.8404, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7482/10000, Train Loss: 1.0697, Train Accuracy: 0.8471, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7483/10000, Train Loss: 1.0724, Train Accuracy: 0.8404, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7484/10000, Train Loss: 1.0808, Train Accuracy: 0.8382, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7485/10000, Train Loss: 1.0822, Train Accuracy: 0.8270, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7486/10000, Train Loss: 1.0734, Train Accuracy: 0.8404, Val Loss: 1.1822, Val Accuracy: 0.7321 Epoch 7487/10000, Train Loss: 1.0762, Train Accuracy: 0.8348, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7488/10000, Train Loss: 1.0668, Train Accuracy: 0.8504, Val Loss: 1.1818, Val Accuracy: 0.7321 Epoch 7489/10000, Train Loss: 1.0746, Train Accuracy: 0.8292, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7490/10000, Train Loss: 1.0778, Train Accuracy: 0.8404, Val Loss: 1.1820, Val Accuracy: 0.7321 Epoch 7491/10000, Train Loss: 1.0849, Train Accuracy: 0.8248, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7492/10000, Train Loss: 1.0644, Train Accuracy: 0.8482, Val Loss: 1.1821, Val Accuracy: 0.7321 Epoch 7493/10000, Train Loss: 1.0711, Train Accuracy: 0.8382, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7494/10000, Train Loss: 1.0816, Train Accuracy: 0.8281, Val Loss: 1.1815, Val Accuracy: 0.7277 Epoch 7495/10000, Train Loss: 1.0790, Train Accuracy: 0.8259, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7496/10000, Train Loss: 1.0718, Train Accuracy: 0.8449, Val Loss: 1.1815, Val Accuracy: 0.7277 Epoch 7497/10000, Train Loss: 1.0769, Train Accuracy: 0.8426, Val Loss: 1.1815, Val Accuracy: 0.7277 Epoch 7498/10000, Train Loss: 1.0843, Train Accuracy: 0.8248, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7499/10000, Train Loss: 1.0616, Train Accuracy: 0.8538, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7500/10000, Train Loss: 1.0724, Train Accuracy: 0.8371, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7501/10000, Train Loss: 1.0819, Train Accuracy: 0.8326, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7502/10000, Train Loss: 1.0583, Train Accuracy: 0.8516, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7503/10000, Train Loss: 1.0851, Train Accuracy: 0.8214, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7504/10000, Train Loss: 1.0635, Train Accuracy: 0.8438, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7505/10000, Train Loss: 1.0748, Train Accuracy: 0.8382, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7506/10000, Train Loss: 1.0720, Train Accuracy: 0.8482, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7507/10000, Train Loss: 1.0789, Train Accuracy: 0.8326, Val Loss: 1.1818, Val Accuracy: 0.7321 Epoch 7508/10000, Train Loss: 1.0829, Train Accuracy: 0.8281, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7509/10000, Train Loss: 1.0765, Train Accuracy: 0.8371, Val Loss: 1.1816, Val Accuracy: 0.7277 Epoch 7510/10000, Train Loss: 1.0752, Train Accuracy: 0.8426, Val Loss: 1.1814, Val Accuracy: 0.7321 Epoch 7511/10000, Train Loss: 1.0789, Train Accuracy: 0.8315, Val Loss: 1.1813, Val Accuracy: 0.7321 Epoch 7512/10000, Train Loss: 1.0765, Train Accuracy: 0.8315, Val Loss: 1.1812, Val Accuracy: 0.7321 Epoch 7513/10000, Train Loss: 1.0821, Train Accuracy: 0.8237, Val Loss: 1.1816, Val Accuracy: 0.7321 Epoch 7514/10000, Train Loss: 1.0865, Train Accuracy: 0.8225, Val Loss: 1.1817, Val Accuracy: 0.7321 Epoch 7515/10000, Train Loss: 1.0730, Train Accuracy: 0.8382, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7516/10000, Train Loss: 1.0777, Train Accuracy: 0.8337, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7517/10000, Train Loss: 1.0750, Train Accuracy: 0.8371, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7518/10000, Train Loss: 1.0571, Train Accuracy: 0.8583, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7519/10000, Train Loss: 1.0598, Train Accuracy: 0.8560, Val Loss: 1.1825, Val Accuracy: 0.7232 Epoch 7520/10000, Train Loss: 1.0819, Train Accuracy: 0.8203, Val Loss: 1.1828, Val Accuracy: 0.7232 Epoch 7521/10000, Train Loss: 1.0885, Train Accuracy: 0.8270, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7522/10000, Train Loss: 1.0770, Train Accuracy: 0.8393, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7523/10000, Train Loss: 1.0894, Train Accuracy: 0.8192, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7524/10000, Train Loss: 1.0769, Train Accuracy: 0.8371, Val Loss: 1.1826, Val Accuracy: 0.7232 Epoch 7525/10000, Train Loss: 1.0723, Train Accuracy: 0.8371, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7526/10000, Train Loss: 1.0830, Train Accuracy: 0.8225, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7527/10000, Train Loss: 1.0881, Train Accuracy: 0.8203, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7528/10000, Train Loss: 1.0636, Train Accuracy: 0.8516, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7529/10000, Train Loss: 1.0716, Train Accuracy: 0.8438, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7530/10000, Train Loss: 1.0720, Train Accuracy: 0.8393, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7531/10000, Train Loss: 1.0674, Train Accuracy: 0.8471, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7532/10000, Train Loss: 1.0593, Train Accuracy: 0.8527, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7533/10000, Train Loss: 1.0717, Train Accuracy: 0.8382, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7534/10000, Train Loss: 1.0707, Train Accuracy: 0.8326, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7535/10000, Train Loss: 1.0848, Train Accuracy: 0.8225, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7536/10000, Train Loss: 1.0738, Train Accuracy: 0.8438, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7537/10000, Train Loss: 1.0618, Train Accuracy: 0.8493, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7538/10000, Train Loss: 1.0768, Train Accuracy: 0.8348, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7539/10000, Train Loss: 1.0768, Train Accuracy: 0.8348, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7540/10000, Train Loss: 1.0734, Train Accuracy: 0.8382, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7541/10000, Train Loss: 1.0761, Train Accuracy: 0.8326, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7542/10000, Train Loss: 1.0704, Train Accuracy: 0.8438, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7543/10000, Train Loss: 1.0803, Train Accuracy: 0.8304, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7544/10000, Train Loss: 1.0689, Train Accuracy: 0.8426, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7545/10000, Train Loss: 1.0737, Train Accuracy: 0.8449, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7546/10000, Train Loss: 1.0685, Train Accuracy: 0.8460, Val Loss: 1.1830, Val Accuracy: 0.7277 Epoch 7547/10000, Train Loss: 1.0763, Train Accuracy: 0.8371, Val Loss: 1.1829, Val Accuracy: 0.7277 Epoch 7548/10000, Train Loss: 1.0771, Train Accuracy: 0.8393, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7549/10000, Train Loss: 1.0721, Train Accuracy: 0.8426, Val Loss: 1.1828, Val Accuracy: 0.7277 Epoch 7550/10000, Train Loss: 1.0762, Train Accuracy: 0.8315, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7551/10000, Train Loss: 1.0716, Train Accuracy: 0.8438, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7552/10000, Train Loss: 1.0720, Train Accuracy: 0.8393, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7553/10000, Train Loss: 1.0703, Train Accuracy: 0.8449, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7554/10000, Train Loss: 1.0685, Train Accuracy: 0.8471, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7555/10000, Train Loss: 1.0758, Train Accuracy: 0.8359, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7556/10000, Train Loss: 1.0671, Train Accuracy: 0.8504, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7557/10000, Train Loss: 1.0760, Train Accuracy: 0.8393, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7558/10000, Train Loss: 1.0793, Train Accuracy: 0.8348, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7559/10000, Train Loss: 1.0706, Train Accuracy: 0.8393, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7560/10000, Train Loss: 1.0710, Train Accuracy: 0.8382, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7561/10000, Train Loss: 1.0693, Train Accuracy: 0.8404, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7562/10000, Train Loss: 1.0767, Train Accuracy: 0.8326, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7563/10000, Train Loss: 1.0873, Train Accuracy: 0.8192, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7564/10000, Train Loss: 1.0768, Train Accuracy: 0.8348, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7565/10000, Train Loss: 1.0751, Train Accuracy: 0.8482, Val Loss: 1.1827, Val Accuracy: 0.7277 Epoch 7566/10000, Train Loss: 1.0762, Train Accuracy: 0.8337, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7567/10000, Train Loss: 1.0646, Train Accuracy: 0.8493, Val Loss: 1.1826, Val Accuracy: 0.7277 Epoch 7568/10000, Train Loss: 1.0716, Train Accuracy: 0.8426, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7569/10000, Train Loss: 1.0666, Train Accuracy: 0.8438, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7570/10000, Train Loss: 1.0739, Train Accuracy: 0.8438, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7571/10000, Train Loss: 1.0895, Train Accuracy: 0.8125, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7572/10000, Train Loss: 1.0700, Train Accuracy: 0.8426, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7573/10000, Train Loss: 1.0766, Train Accuracy: 0.8348, Val Loss: 1.1816, Val Accuracy: 0.7277 Epoch 7574/10000, Train Loss: 1.0729, Train Accuracy: 0.8382, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7575/10000, Train Loss: 1.0746, Train Accuracy: 0.8348, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7576/10000, Train Loss: 1.0876, Train Accuracy: 0.8270, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7577/10000, Train Loss: 1.0790, Train Accuracy: 0.8292, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7578/10000, Train Loss: 1.0650, Train Accuracy: 0.8493, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7579/10000, Train Loss: 1.0640, Train Accuracy: 0.8527, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7580/10000, Train Loss: 1.0863, Train Accuracy: 0.8203, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7581/10000, Train Loss: 1.0670, Train Accuracy: 0.8460, Val Loss: 1.1824, Val Accuracy: 0.7277 Epoch 7582/10000, Train Loss: 1.0851, Train Accuracy: 0.8292, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7583/10000, Train Loss: 1.0688, Train Accuracy: 0.8404, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7584/10000, Train Loss: 1.0628, Train Accuracy: 0.8426, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7585/10000, Train Loss: 1.0809, Train Accuracy: 0.8248, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7586/10000, Train Loss: 1.0687, Train Accuracy: 0.8493, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7587/10000, Train Loss: 1.0631, Train Accuracy: 0.8460, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7588/10000, Train Loss: 1.0732, Train Accuracy: 0.8438, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7589/10000, Train Loss: 1.0722, Train Accuracy: 0.8371, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7590/10000, Train Loss: 1.0667, Train Accuracy: 0.8471, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7591/10000, Train Loss: 1.0666, Train Accuracy: 0.8426, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7592/10000, Train Loss: 1.0718, Train Accuracy: 0.8449, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7593/10000, Train Loss: 1.0633, Train Accuracy: 0.8538, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7594/10000, Train Loss: 1.0722, Train Accuracy: 0.8426, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7595/10000, Train Loss: 1.0633, Train Accuracy: 0.8527, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7596/10000, Train Loss: 1.0763, Train Accuracy: 0.8382, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7597/10000, Train Loss: 1.0786, Train Accuracy: 0.8270, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7598/10000, Train Loss: 1.0694, Train Accuracy: 0.8449, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7599/10000, Train Loss: 1.0721, Train Accuracy: 0.8393, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7600/10000, Train Loss: 1.0726, Train Accuracy: 0.8348, Val Loss: 1.1822, Val Accuracy: 0.7232 Epoch 7601/10000, Train Loss: 1.0760, Train Accuracy: 0.8337, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7602/10000, Train Loss: 1.0894, Train Accuracy: 0.8092, Val Loss: 1.1822, Val Accuracy: 0.7232 Epoch 7603/10000, Train Loss: 1.0776, Train Accuracy: 0.8393, Val Loss: 1.1822, Val Accuracy: 0.7232 Epoch 7604/10000, Train Loss: 1.0779, Train Accuracy: 0.8326, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7605/10000, Train Loss: 1.0745, Train Accuracy: 0.8404, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7606/10000, Train Loss: 1.0690, Train Accuracy: 0.8460, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7607/10000, Train Loss: 1.0766, Train Accuracy: 0.8315, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7608/10000, Train Loss: 1.0817, Train Accuracy: 0.8337, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7609/10000, Train Loss: 1.0805, Train Accuracy: 0.8304, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7610/10000, Train Loss: 1.0649, Train Accuracy: 0.8460, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7611/10000, Train Loss: 1.0777, Train Accuracy: 0.8382, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7612/10000, Train Loss: 1.0782, Train Accuracy: 0.8315, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7613/10000, Train Loss: 1.0747, Train Accuracy: 0.8460, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7614/10000, Train Loss: 1.0779, Train Accuracy: 0.8348, Val Loss: 1.1819, Val Accuracy: 0.7232 Epoch 7615/10000, Train Loss: 1.0699, Train Accuracy: 0.8527, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7616/10000, Train Loss: 1.0664, Train Accuracy: 0.8438, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7617/10000, Train Loss: 1.0650, Train Accuracy: 0.8482, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7618/10000, Train Loss: 1.0821, Train Accuracy: 0.8337, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7619/10000, Train Loss: 1.0750, Train Accuracy: 0.8426, Val Loss: 1.1819, Val Accuracy: 0.7232 Epoch 7620/10000, Train Loss: 1.0641, Train Accuracy: 0.8493, Val Loss: 1.1819, Val Accuracy: 0.7232 Epoch 7621/10000, Train Loss: 1.0819, Train Accuracy: 0.8237, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7622/10000, Train Loss: 1.0725, Train Accuracy: 0.8449, Val Loss: 1.1819, Val Accuracy: 0.7232 Epoch 7623/10000, Train Loss: 1.0670, Train Accuracy: 0.8426, Val Loss: 1.1819, Val Accuracy: 0.7232 Epoch 7624/10000, Train Loss: 1.0738, Train Accuracy: 0.8359, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7625/10000, Train Loss: 1.0671, Train Accuracy: 0.8438, Val Loss: 1.1819, Val Accuracy: 0.7232 Epoch 7626/10000, Train Loss: 1.0708, Train Accuracy: 0.8404, Val Loss: 1.1816, Val Accuracy: 0.7232 Epoch 7627/10000, Train Loss: 1.0767, Train Accuracy: 0.8292, Val Loss: 1.1815, Val Accuracy: 0.7232 Epoch 7628/10000, Train Loss: 1.0674, Train Accuracy: 0.8460, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7629/10000, Train Loss: 1.0701, Train Accuracy: 0.8438, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7630/10000, Train Loss: 1.0728, Train Accuracy: 0.8426, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7631/10000, Train Loss: 1.0705, Train Accuracy: 0.8415, Val Loss: 1.1815, Val Accuracy: 0.7232 Epoch 7632/10000, Train Loss: 1.0696, Train Accuracy: 0.8415, Val Loss: 1.1816, Val Accuracy: 0.7232 Epoch 7633/10000, Train Loss: 1.0682, Train Accuracy: 0.8371, Val Loss: 1.1816, Val Accuracy: 0.7232 Epoch 7634/10000, Train Loss: 1.0751, Train Accuracy: 0.8371, Val Loss: 1.1814, Val Accuracy: 0.7232 Epoch 7635/10000, Train Loss: 1.0664, Train Accuracy: 0.8404, Val Loss: 1.1817, Val Accuracy: 0.7232 Epoch 7636/10000, Train Loss: 1.0785, Train Accuracy: 0.8292, Val Loss: 1.1815, Val Accuracy: 0.7232 Epoch 7637/10000, Train Loss: 1.0774, Train Accuracy: 0.8315, Val Loss: 1.1814, Val Accuracy: 0.7232 Epoch 7638/10000, Train Loss: 1.0673, Train Accuracy: 0.8482, Val Loss: 1.1813, Val Accuracy: 0.7232 Epoch 7639/10000, Train Loss: 1.0549, Train Accuracy: 0.8638, Val Loss: 1.1812, Val Accuracy: 0.7232 Epoch 7640/10000, Train Loss: 1.0633, Train Accuracy: 0.8527, Val Loss: 1.1811, Val Accuracy: 0.7232 Epoch 7641/10000, Train Loss: 1.0629, Train Accuracy: 0.8516, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7642/10000, Train Loss: 1.0692, Train Accuracy: 0.8438, Val Loss: 1.1809, Val Accuracy: 0.7232 Epoch 7643/10000, Train Loss: 1.0692, Train Accuracy: 0.8471, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7644/10000, Train Loss: 1.0764, Train Accuracy: 0.8404, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7645/10000, Train Loss: 1.0638, Train Accuracy: 0.8504, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7646/10000, Train Loss: 1.0713, Train Accuracy: 0.8292, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7647/10000, Train Loss: 1.0664, Train Accuracy: 0.8538, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7648/10000, Train Loss: 1.0639, Train Accuracy: 0.8560, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7649/10000, Train Loss: 1.0720, Train Accuracy: 0.8393, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7650/10000, Train Loss: 1.0742, Train Accuracy: 0.8438, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7651/10000, Train Loss: 1.0735, Train Accuracy: 0.8371, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7652/10000, Train Loss: 1.0609, Train Accuracy: 0.8527, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7653/10000, Train Loss: 1.0590, Train Accuracy: 0.8482, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7654/10000, Train Loss: 1.0583, Train Accuracy: 0.8527, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7655/10000, Train Loss: 1.0733, Train Accuracy: 0.8449, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7656/10000, Train Loss: 1.0688, Train Accuracy: 0.8482, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7657/10000, Train Loss: 1.0625, Train Accuracy: 0.8516, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7658/10000, Train Loss: 1.0599, Train Accuracy: 0.8527, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7659/10000, Train Loss: 1.0760, Train Accuracy: 0.8404, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7660/10000, Train Loss: 1.0683, Train Accuracy: 0.8471, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7661/10000, Train Loss: 1.0706, Train Accuracy: 0.8404, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7662/10000, Train Loss: 1.0621, Train Accuracy: 0.8516, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7663/10000, Train Loss: 1.0683, Train Accuracy: 0.8415, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7664/10000, Train Loss: 1.0727, Train Accuracy: 0.8404, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7665/10000, Train Loss: 1.0651, Train Accuracy: 0.8549, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7666/10000, Train Loss: 1.0653, Train Accuracy: 0.8471, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7667/10000, Train Loss: 1.0653, Train Accuracy: 0.8449, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7668/10000, Train Loss: 1.0718, Train Accuracy: 0.8371, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7669/10000, Train Loss: 1.0741, Train Accuracy: 0.8348, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7670/10000, Train Loss: 1.0710, Train Accuracy: 0.8371, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7671/10000, Train Loss: 1.0688, Train Accuracy: 0.8371, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7672/10000, Train Loss: 1.0682, Train Accuracy: 0.8471, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7673/10000, Train Loss: 1.0686, Train Accuracy: 0.8415, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7674/10000, Train Loss: 1.0634, Train Accuracy: 0.8516, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7675/10000, Train Loss: 1.0598, Train Accuracy: 0.8527, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7676/10000, Train Loss: 1.0640, Train Accuracy: 0.8460, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7677/10000, Train Loss: 1.0698, Train Accuracy: 0.8337, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7678/10000, Train Loss: 1.0756, Train Accuracy: 0.8371, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7679/10000, Train Loss: 1.0628, Train Accuracy: 0.8482, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7680/10000, Train Loss: 1.0694, Train Accuracy: 0.8471, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7681/10000, Train Loss: 1.0678, Train Accuracy: 0.8471, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7682/10000, Train Loss: 1.0753, Train Accuracy: 0.8404, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7683/10000, Train Loss: 1.0609, Train Accuracy: 0.8571, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7684/10000, Train Loss: 1.0679, Train Accuracy: 0.8449, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7685/10000, Train Loss: 1.0784, Train Accuracy: 0.8371, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7686/10000, Train Loss: 1.0577, Train Accuracy: 0.8583, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7687/10000, Train Loss: 1.0688, Train Accuracy: 0.8493, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7688/10000, Train Loss: 1.0591, Train Accuracy: 0.8549, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7689/10000, Train Loss: 1.0714, Train Accuracy: 0.8404, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7690/10000, Train Loss: 1.0660, Train Accuracy: 0.8460, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7691/10000, Train Loss: 1.0692, Train Accuracy: 0.8337, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7692/10000, Train Loss: 1.0776, Train Accuracy: 0.8315, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7693/10000, Train Loss: 1.0679, Train Accuracy: 0.8426, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7694/10000, Train Loss: 1.0595, Train Accuracy: 0.8538, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7695/10000, Train Loss: 1.0661, Train Accuracy: 0.8471, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7696/10000, Train Loss: 1.0761, Train Accuracy: 0.8393, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7697/10000, Train Loss: 1.0644, Train Accuracy: 0.8449, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7698/10000, Train Loss: 1.0660, Train Accuracy: 0.8449, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7699/10000, Train Loss: 1.0670, Train Accuracy: 0.8504, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7700/10000, Train Loss: 1.0790, Train Accuracy: 0.8337, Val Loss: 1.1816, Val Accuracy: 0.7277 Epoch 7701/10000, Train Loss: 1.0637, Train Accuracy: 0.8538, Val Loss: 1.1815, Val Accuracy: 0.7277 Epoch 7702/10000, Train Loss: 1.0792, Train Accuracy: 0.8281, Val Loss: 1.1816, Val Accuracy: 0.7277 Epoch 7703/10000, Train Loss: 1.0623, Train Accuracy: 0.8560, Val Loss: 1.1815, Val Accuracy: 0.7277 Epoch 7704/10000, Train Loss: 1.0652, Train Accuracy: 0.8471, Val Loss: 1.1814, Val Accuracy: 0.7232 Epoch 7705/10000, Train Loss: 1.0799, Train Accuracy: 0.8326, Val Loss: 1.1813, Val Accuracy: 0.7232 Epoch 7706/10000, Train Loss: 1.0757, Train Accuracy: 0.8326, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7707/10000, Train Loss: 1.0716, Train Accuracy: 0.8426, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7708/10000, Train Loss: 1.0740, Train Accuracy: 0.8359, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7709/10000, Train Loss: 1.0607, Train Accuracy: 0.8583, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7710/10000, Train Loss: 1.0523, Train Accuracy: 0.8583, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7711/10000, Train Loss: 1.0738, Train Accuracy: 0.8326, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7712/10000, Train Loss: 1.0659, Train Accuracy: 0.8482, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7713/10000, Train Loss: 1.0645, Train Accuracy: 0.8415, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7714/10000, Train Loss: 1.0696, Train Accuracy: 0.8460, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7715/10000, Train Loss: 1.0830, Train Accuracy: 0.8281, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7716/10000, Train Loss: 1.0733, Train Accuracy: 0.8371, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7717/10000, Train Loss: 1.0670, Train Accuracy: 0.8471, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7718/10000, Train Loss: 1.0525, Train Accuracy: 0.8650, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7719/10000, Train Loss: 1.0660, Train Accuracy: 0.8471, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7720/10000, Train Loss: 1.0765, Train Accuracy: 0.8304, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7721/10000, Train Loss: 1.0718, Train Accuracy: 0.8415, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7722/10000, Train Loss: 1.0655, Train Accuracy: 0.8449, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7723/10000, Train Loss: 1.0775, Train Accuracy: 0.8337, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7724/10000, Train Loss: 1.0619, Train Accuracy: 0.8482, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7725/10000, Train Loss: 1.0734, Train Accuracy: 0.8337, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7726/10000, Train Loss: 1.0771, Train Accuracy: 0.8371, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7727/10000, Train Loss: 1.0578, Train Accuracy: 0.8583, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7728/10000, Train Loss: 1.0711, Train Accuracy: 0.8382, Val Loss: 1.1826, Val Accuracy: 0.7232 Epoch 7729/10000, Train Loss: 1.0783, Train Accuracy: 0.8326, Val Loss: 1.1825, Val Accuracy: 0.7277 Epoch 7730/10000, Train Loss: 1.0670, Train Accuracy: 0.8504, Val Loss: 1.1823, Val Accuracy: 0.7277 Epoch 7731/10000, Train Loss: 1.0698, Train Accuracy: 0.8426, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7732/10000, Train Loss: 1.0638, Train Accuracy: 0.8438, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7733/10000, Train Loss: 1.0769, Train Accuracy: 0.8348, Val Loss: 1.1822, Val Accuracy: 0.7277 Epoch 7734/10000, Train Loss: 1.0681, Train Accuracy: 0.8393, Val Loss: 1.1822, Val Accuracy: 0.7232 Epoch 7735/10000, Train Loss: 1.0831, Train Accuracy: 0.8259, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7736/10000, Train Loss: 1.0743, Train Accuracy: 0.8348, Val Loss: 1.1820, Val Accuracy: 0.7277 Epoch 7737/10000, Train Loss: 1.0770, Train Accuracy: 0.8326, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7738/10000, Train Loss: 1.0721, Train Accuracy: 0.8382, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7739/10000, Train Loss: 1.0770, Train Accuracy: 0.8371, Val Loss: 1.1821, Val Accuracy: 0.7232 Epoch 7740/10000, Train Loss: 1.0693, Train Accuracy: 0.8415, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7741/10000, Train Loss: 1.0628, Train Accuracy: 0.8471, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7742/10000, Train Loss: 1.0583, Train Accuracy: 0.8571, Val Loss: 1.1817, Val Accuracy: 0.7277 Epoch 7743/10000, Train Loss: 1.0614, Train Accuracy: 0.8549, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7744/10000, Train Loss: 1.0690, Train Accuracy: 0.8393, Val Loss: 1.1821, Val Accuracy: 0.7277 Epoch 7745/10000, Train Loss: 1.0654, Train Accuracy: 0.8460, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7746/10000, Train Loss: 1.0598, Train Accuracy: 0.8527, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7747/10000, Train Loss: 1.0682, Train Accuracy: 0.8371, Val Loss: 1.1820, Val Accuracy: 0.7232 Epoch 7748/10000, Train Loss: 1.0745, Train Accuracy: 0.8359, Val Loss: 1.1818, Val Accuracy: 0.7232 Epoch 7749/10000, Train Loss: 1.0612, Train Accuracy: 0.8538, Val Loss: 1.1819, Val Accuracy: 0.7277 Epoch 7750/10000, Train Loss: 1.0619, Train Accuracy: 0.8560, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7751/10000, Train Loss: 1.0670, Train Accuracy: 0.8493, Val Loss: 1.1818, Val Accuracy: 0.7277 Epoch 7752/10000, Train Loss: 1.0714, Train Accuracy: 0.8482, Val Loss: 1.1816, Val Accuracy: 0.7277 Epoch 7753/10000, Train Loss: 1.0704, Train Accuracy: 0.8415, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7754/10000, Train Loss: 1.0616, Train Accuracy: 0.8415, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7755/10000, Train Loss: 1.0696, Train Accuracy: 0.8438, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7756/10000, Train Loss: 1.0596, Train Accuracy: 0.8516, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7757/10000, Train Loss: 1.0803, Train Accuracy: 0.8281, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7758/10000, Train Loss: 1.0712, Train Accuracy: 0.8393, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7759/10000, Train Loss: 1.0764, Train Accuracy: 0.8371, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7760/10000, Train Loss: 1.0715, Train Accuracy: 0.8460, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7761/10000, Train Loss: 1.0647, Train Accuracy: 0.8426, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7762/10000, Train Loss: 1.0667, Train Accuracy: 0.8438, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7763/10000, Train Loss: 1.0643, Train Accuracy: 0.8449, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7764/10000, Train Loss: 1.0624, Train Accuracy: 0.8504, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7765/10000, Train Loss: 1.0589, Train Accuracy: 0.8571, Val Loss: 1.1816, Val Accuracy: 0.7277 Epoch 7766/10000, Train Loss: 1.0602, Train Accuracy: 0.8527, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7767/10000, Train Loss: 1.0649, Train Accuracy: 0.8493, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7768/10000, Train Loss: 1.0708, Train Accuracy: 0.8359, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7769/10000, Train Loss: 1.0779, Train Accuracy: 0.8237, Val Loss: 1.1809, Val Accuracy: 0.7232 Epoch 7770/10000, Train Loss: 1.0750, Train Accuracy: 0.8359, Val Loss: 1.1811, Val Accuracy: 0.7232 Epoch 7771/10000, Train Loss: 1.0699, Train Accuracy: 0.8449, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7772/10000, Train Loss: 1.0536, Train Accuracy: 0.8638, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7773/10000, Train Loss: 1.0652, Train Accuracy: 0.8438, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7774/10000, Train Loss: 1.0681, Train Accuracy: 0.8426, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7775/10000, Train Loss: 1.0603, Train Accuracy: 0.8482, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7776/10000, Train Loss: 1.0530, Train Accuracy: 0.8638, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7777/10000, Train Loss: 1.0671, Train Accuracy: 0.8415, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7778/10000, Train Loss: 1.0766, Train Accuracy: 0.8304, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7779/10000, Train Loss: 1.0731, Train Accuracy: 0.8371, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7780/10000, Train Loss: 1.0671, Train Accuracy: 0.8460, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7781/10000, Train Loss: 1.0725, Train Accuracy: 0.8460, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7782/10000, Train Loss: 1.0731, Train Accuracy: 0.8382, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7783/10000, Train Loss: 1.0709, Train Accuracy: 0.8460, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7784/10000, Train Loss: 1.0651, Train Accuracy: 0.8460, Val Loss: 1.1814, Val Accuracy: 0.7277 Epoch 7785/10000, Train Loss: 1.0664, Train Accuracy: 0.8482, Val Loss: 1.1813, Val Accuracy: 0.7277 Epoch 7786/10000, Train Loss: 1.0725, Train Accuracy: 0.8426, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7787/10000, Train Loss: 1.0657, Train Accuracy: 0.8449, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7788/10000, Train Loss: 1.0729, Train Accuracy: 0.8382, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7789/10000, Train Loss: 1.0496, Train Accuracy: 0.8683, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7790/10000, Train Loss: 1.0672, Train Accuracy: 0.8460, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7791/10000, Train Loss: 1.0584, Train Accuracy: 0.8571, Val Loss: 1.1812, Val Accuracy: 0.7277 Epoch 7792/10000, Train Loss: 1.0569, Train Accuracy: 0.8594, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7793/10000, Train Loss: 1.0822, Train Accuracy: 0.8292, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7794/10000, Train Loss: 1.0708, Train Accuracy: 0.8449, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7795/10000, Train Loss: 1.0663, Train Accuracy: 0.8438, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7796/10000, Train Loss: 1.0791, Train Accuracy: 0.8315, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7797/10000, Train Loss: 1.0786, Train Accuracy: 0.8259, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7798/10000, Train Loss: 1.0633, Train Accuracy: 0.8538, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7799/10000, Train Loss: 1.0626, Train Accuracy: 0.8527, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7800/10000, Train Loss: 1.0626, Train Accuracy: 0.8415, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7801/10000, Train Loss: 1.0782, Train Accuracy: 0.8337, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7802/10000, Train Loss: 1.0743, Train Accuracy: 0.8393, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7803/10000, Train Loss: 1.0789, Train Accuracy: 0.8304, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7804/10000, Train Loss: 1.0714, Train Accuracy: 0.8415, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7805/10000, Train Loss: 1.0665, Train Accuracy: 0.8426, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7806/10000, Train Loss: 1.0649, Train Accuracy: 0.8527, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7807/10000, Train Loss: 1.0577, Train Accuracy: 0.8493, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7808/10000, Train Loss: 1.0675, Train Accuracy: 0.8449, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7809/10000, Train Loss: 1.0631, Train Accuracy: 0.8527, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7810/10000, Train Loss: 1.0726, Train Accuracy: 0.8404, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7811/10000, Train Loss: 1.0579, Train Accuracy: 0.8527, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7812/10000, Train Loss: 1.0636, Train Accuracy: 0.8504, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7813/10000, Train Loss: 1.0661, Train Accuracy: 0.8549, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7814/10000, Train Loss: 1.0780, Train Accuracy: 0.8337, Val Loss: 1.1807, Val Accuracy: 0.7277 Epoch 7815/10000, Train Loss: 1.0696, Train Accuracy: 0.8404, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7816/10000, Train Loss: 1.0697, Train Accuracy: 0.8449, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7817/10000, Train Loss: 1.0626, Train Accuracy: 0.8482, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7818/10000, Train Loss: 1.0620, Train Accuracy: 0.8504, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7819/10000, Train Loss: 1.0692, Train Accuracy: 0.8426, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7820/10000, Train Loss: 1.0637, Train Accuracy: 0.8516, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7821/10000, Train Loss: 1.0667, Train Accuracy: 0.8571, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7822/10000, Train Loss: 1.0502, Train Accuracy: 0.8605, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7823/10000, Train Loss: 1.0654, Train Accuracy: 0.8482, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7824/10000, Train Loss: 1.0717, Train Accuracy: 0.8438, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7825/10000, Train Loss: 1.0813, Train Accuracy: 0.8292, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7826/10000, Train Loss: 1.0603, Train Accuracy: 0.8493, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7827/10000, Train Loss: 1.0673, Train Accuracy: 0.8449, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7828/10000, Train Loss: 1.0646, Train Accuracy: 0.8504, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7829/10000, Train Loss: 1.0719, Train Accuracy: 0.8415, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7830/10000, Train Loss: 1.0682, Train Accuracy: 0.8482, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7831/10000, Train Loss: 1.0696, Train Accuracy: 0.8404, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7832/10000, Train Loss: 1.0655, Train Accuracy: 0.8527, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7833/10000, Train Loss: 1.0667, Train Accuracy: 0.8393, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7834/10000, Train Loss: 1.0611, Train Accuracy: 0.8493, Val Loss: 1.1793, Val Accuracy: 0.7277 Epoch 7835/10000, Train Loss: 1.0706, Train Accuracy: 0.8438, Val Loss: 1.1791, Val Accuracy: 0.7277 Epoch 7836/10000, Train Loss: 1.0607, Train Accuracy: 0.8527, Val Loss: 1.1790, Val Accuracy: 0.7277 Epoch 7837/10000, Train Loss: 1.0614, Train Accuracy: 0.8493, Val Loss: 1.1791, Val Accuracy: 0.7277 Epoch 7838/10000, Train Loss: 1.0570, Train Accuracy: 0.8560, Val Loss: 1.1792, Val Accuracy: 0.7321 Epoch 7839/10000, Train Loss: 1.0557, Train Accuracy: 0.8560, Val Loss: 1.1792, Val Accuracy: 0.7277 Epoch 7840/10000, Train Loss: 1.0745, Train Accuracy: 0.8359, Val Loss: 1.1794, Val Accuracy: 0.7277 Epoch 7841/10000, Train Loss: 1.0636, Train Accuracy: 0.8471, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7842/10000, Train Loss: 1.0702, Train Accuracy: 0.8393, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7843/10000, Train Loss: 1.0704, Train Accuracy: 0.8348, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7844/10000, Train Loss: 1.0718, Train Accuracy: 0.8393, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7845/10000, Train Loss: 1.0699, Train Accuracy: 0.8426, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7846/10000, Train Loss: 1.0629, Train Accuracy: 0.8438, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7847/10000, Train Loss: 1.0611, Train Accuracy: 0.8516, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7848/10000, Train Loss: 1.0745, Train Accuracy: 0.8371, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7849/10000, Train Loss: 1.0728, Train Accuracy: 0.8438, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7850/10000, Train Loss: 1.0657, Train Accuracy: 0.8471, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7851/10000, Train Loss: 1.0573, Train Accuracy: 0.8527, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7852/10000, Train Loss: 1.0666, Train Accuracy: 0.8449, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7853/10000, Train Loss: 1.0664, Train Accuracy: 0.8471, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7854/10000, Train Loss: 1.0724, Train Accuracy: 0.8326, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7855/10000, Train Loss: 1.0590, Train Accuracy: 0.8549, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7856/10000, Train Loss: 1.0566, Train Accuracy: 0.8594, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7857/10000, Train Loss: 1.0738, Train Accuracy: 0.8304, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7858/10000, Train Loss: 1.0723, Train Accuracy: 0.8371, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7859/10000, Train Loss: 1.0478, Train Accuracy: 0.8616, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7860/10000, Train Loss: 1.0667, Train Accuracy: 0.8438, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7861/10000, Train Loss: 1.0676, Train Accuracy: 0.8393, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7862/10000, Train Loss: 1.0608, Train Accuracy: 0.8527, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7863/10000, Train Loss: 1.0744, Train Accuracy: 0.8348, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7864/10000, Train Loss: 1.0518, Train Accuracy: 0.8594, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7865/10000, Train Loss: 1.0528, Train Accuracy: 0.8661, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7866/10000, Train Loss: 1.0773, Train Accuracy: 0.8292, Val Loss: 1.1796, Val Accuracy: 0.7277 Epoch 7867/10000, Train Loss: 1.0601, Train Accuracy: 0.8538, Val Loss: 1.1796, Val Accuracy: 0.7277 Epoch 7868/10000, Train Loss: 1.0558, Train Accuracy: 0.8605, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7869/10000, Train Loss: 1.0680, Train Accuracy: 0.8471, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7870/10000, Train Loss: 1.0722, Train Accuracy: 0.8348, Val Loss: 1.1794, Val Accuracy: 0.7277 Epoch 7871/10000, Train Loss: 1.0640, Train Accuracy: 0.8415, Val Loss: 1.1792, Val Accuracy: 0.7277 Epoch 7872/10000, Train Loss: 1.0743, Train Accuracy: 0.8348, Val Loss: 1.1794, Val Accuracy: 0.7277 Epoch 7873/10000, Train Loss: 1.0523, Train Accuracy: 0.8616, Val Loss: 1.1794, Val Accuracy: 0.7277 Epoch 7874/10000, Train Loss: 1.0659, Train Accuracy: 0.8482, Val Loss: 1.1793, Val Accuracy: 0.7277 Epoch 7875/10000, Train Loss: 1.0726, Train Accuracy: 0.8382, Val Loss: 1.1791, Val Accuracy: 0.7277 Epoch 7876/10000, Train Loss: 1.0650, Train Accuracy: 0.8482, Val Loss: 1.1791, Val Accuracy: 0.7277 Epoch 7877/10000, Train Loss: 1.0627, Train Accuracy: 0.8493, Val Loss: 1.1791, Val Accuracy: 0.7277 Epoch 7878/10000, Train Loss: 1.0571, Train Accuracy: 0.8538, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7879/10000, Train Loss: 1.0568, Train Accuracy: 0.8471, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7880/10000, Train Loss: 1.0644, Train Accuracy: 0.8460, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7881/10000, Train Loss: 1.0628, Train Accuracy: 0.8493, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7882/10000, Train Loss: 1.0665, Train Accuracy: 0.8471, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7883/10000, Train Loss: 1.0555, Train Accuracy: 0.8650, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7884/10000, Train Loss: 1.0687, Train Accuracy: 0.8404, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7885/10000, Train Loss: 1.0635, Train Accuracy: 0.8460, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7886/10000, Train Loss: 1.0500, Train Accuracy: 0.8694, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7887/10000, Train Loss: 1.0718, Train Accuracy: 0.8337, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7888/10000, Train Loss: 1.0633, Train Accuracy: 0.8460, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7889/10000, Train Loss: 1.0613, Train Accuracy: 0.8460, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7890/10000, Train Loss: 1.0698, Train Accuracy: 0.8315, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7891/10000, Train Loss: 1.0519, Train Accuracy: 0.8638, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7892/10000, Train Loss: 1.0713, Train Accuracy: 0.8382, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7893/10000, Train Loss: 1.0635, Train Accuracy: 0.8460, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7894/10000, Train Loss: 1.0728, Train Accuracy: 0.8337, Val Loss: 1.1796, Val Accuracy: 0.7277 Epoch 7895/10000, Train Loss: 1.0554, Train Accuracy: 0.8605, Val Loss: 1.1794, Val Accuracy: 0.7277 Epoch 7896/10000, Train Loss: 1.0687, Train Accuracy: 0.8482, Val Loss: 1.1794, Val Accuracy: 0.7277 Epoch 7897/10000, Train Loss: 1.0719, Train Accuracy: 0.8449, Val Loss: 1.1795, Val Accuracy: 0.7277 Epoch 7898/10000, Train Loss: 1.0712, Train Accuracy: 0.8438, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7899/10000, Train Loss: 1.0650, Train Accuracy: 0.8594, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7900/10000, Train Loss: 1.0641, Train Accuracy: 0.8426, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7901/10000, Train Loss: 1.0615, Train Accuracy: 0.8527, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7902/10000, Train Loss: 1.0731, Train Accuracy: 0.8382, Val Loss: 1.1793, Val Accuracy: 0.7277 Epoch 7903/10000, Train Loss: 1.0681, Train Accuracy: 0.8449, Val Loss: 1.1796, Val Accuracy: 0.7277 Epoch 7904/10000, Train Loss: 1.0669, Train Accuracy: 0.8471, Val Loss: 1.1797, Val Accuracy: 0.7277 Epoch 7905/10000, Train Loss: 1.0615, Train Accuracy: 0.8393, Val Loss: 1.1798, Val Accuracy: 0.7277 Epoch 7906/10000, Train Loss: 1.0565, Train Accuracy: 0.8527, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7907/10000, Train Loss: 1.0615, Train Accuracy: 0.8616, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7908/10000, Train Loss: 1.0586, Train Accuracy: 0.8560, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7909/10000, Train Loss: 1.0674, Train Accuracy: 0.8438, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7910/10000, Train Loss: 1.0610, Train Accuracy: 0.8549, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7911/10000, Train Loss: 1.0631, Train Accuracy: 0.8460, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7912/10000, Train Loss: 1.0752, Train Accuracy: 0.8315, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7913/10000, Train Loss: 1.0585, Train Accuracy: 0.8571, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7914/10000, Train Loss: 1.0691, Train Accuracy: 0.8438, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7915/10000, Train Loss: 1.0667, Train Accuracy: 0.8415, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7916/10000, Train Loss: 1.0605, Train Accuracy: 0.8493, Val Loss: 1.1811, Val Accuracy: 0.7277 Epoch 7917/10000, Train Loss: 1.0586, Train Accuracy: 0.8571, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7918/10000, Train Loss: 1.0763, Train Accuracy: 0.8371, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7919/10000, Train Loss: 1.0656, Train Accuracy: 0.8460, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7920/10000, Train Loss: 1.0582, Train Accuracy: 0.8527, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7921/10000, Train Loss: 1.0656, Train Accuracy: 0.8504, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7922/10000, Train Loss: 1.0617, Train Accuracy: 0.8538, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7923/10000, Train Loss: 1.0725, Train Accuracy: 0.8348, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7924/10000, Train Loss: 1.0544, Train Accuracy: 0.8650, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7925/10000, Train Loss: 1.0550, Train Accuracy: 0.8605, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7926/10000, Train Loss: 1.0673, Train Accuracy: 0.8415, Val Loss: 1.1806, Val Accuracy: 0.7277 Epoch 7927/10000, Train Loss: 1.0717, Train Accuracy: 0.8426, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7928/10000, Train Loss: 1.0431, Train Accuracy: 0.8739, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7929/10000, Train Loss: 1.0583, Train Accuracy: 0.8571, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7930/10000, Train Loss: 1.0698, Train Accuracy: 0.8404, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7931/10000, Train Loss: 1.0650, Train Accuracy: 0.8438, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 7932/10000, Train Loss: 1.0630, Train Accuracy: 0.8460, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7933/10000, Train Loss: 1.0686, Train Accuracy: 0.8438, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7934/10000, Train Loss: 1.0773, Train Accuracy: 0.8337, Val Loss: 1.1803, Val Accuracy: 0.7277 Epoch 7935/10000, Train Loss: 1.0643, Train Accuracy: 0.8482, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7936/10000, Train Loss: 1.0637, Train Accuracy: 0.8460, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7937/10000, Train Loss: 1.0685, Train Accuracy: 0.8426, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7938/10000, Train Loss: 1.0668, Train Accuracy: 0.8449, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7939/10000, Train Loss: 1.0635, Train Accuracy: 0.8516, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7940/10000, Train Loss: 1.0590, Train Accuracy: 0.8571, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7941/10000, Train Loss: 1.0608, Train Accuracy: 0.8527, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7942/10000, Train Loss: 1.0590, Train Accuracy: 0.8594, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7943/10000, Train Loss: 1.0768, Train Accuracy: 0.8270, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7944/10000, Train Loss: 1.0629, Train Accuracy: 0.8504, Val Loss: 1.1799, Val Accuracy: 0.7277 Epoch 7945/10000, Train Loss: 1.0749, Train Accuracy: 0.8359, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7946/10000, Train Loss: 1.0556, Train Accuracy: 0.8605, Val Loss: 1.1801, Val Accuracy: 0.7321 Epoch 7947/10000, Train Loss: 1.0499, Train Accuracy: 0.8638, Val Loss: 1.1801, Val Accuracy: 0.7321 Epoch 7948/10000, Train Loss: 1.0835, Train Accuracy: 0.8270, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7949/10000, Train Loss: 1.0598, Train Accuracy: 0.8516, Val Loss: 1.1802, Val Accuracy: 0.7321 Epoch 7950/10000, Train Loss: 1.0605, Train Accuracy: 0.8516, Val Loss: 1.1800, Val Accuracy: 0.7321 Epoch 7951/10000, Train Loss: 1.0779, Train Accuracy: 0.8382, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7952/10000, Train Loss: 1.0766, Train Accuracy: 0.8292, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 7953/10000, Train Loss: 1.0548, Train Accuracy: 0.8549, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7954/10000, Train Loss: 1.0660, Train Accuracy: 0.8460, Val Loss: 1.1805, Val Accuracy: 0.7321 Epoch 7955/10000, Train Loss: 1.0568, Train Accuracy: 0.8516, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7956/10000, Train Loss: 1.0749, Train Accuracy: 0.8359, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7957/10000, Train Loss: 1.0612, Train Accuracy: 0.8471, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7958/10000, Train Loss: 1.0731, Train Accuracy: 0.8382, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7959/10000, Train Loss: 1.0678, Train Accuracy: 0.8438, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7960/10000, Train Loss: 1.0644, Train Accuracy: 0.8471, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 7961/10000, Train Loss: 1.0503, Train Accuracy: 0.8683, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 7962/10000, Train Loss: 1.0757, Train Accuracy: 0.8326, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7963/10000, Train Loss: 1.0616, Train Accuracy: 0.8516, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7964/10000, Train Loss: 1.0628, Train Accuracy: 0.8471, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7965/10000, Train Loss: 1.0722, Train Accuracy: 0.8348, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7966/10000, Train Loss: 1.0653, Train Accuracy: 0.8449, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7967/10000, Train Loss: 1.0639, Train Accuracy: 0.8471, Val Loss: 1.1805, Val Accuracy: 0.7321 Epoch 7968/10000, Train Loss: 1.0458, Train Accuracy: 0.8694, Val Loss: 1.1806, Val Accuracy: 0.7321 Epoch 7969/10000, Train Loss: 1.0681, Train Accuracy: 0.8504, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7970/10000, Train Loss: 1.0701, Train Accuracy: 0.8438, Val Loss: 1.1805, Val Accuracy: 0.7321 Epoch 7971/10000, Train Loss: 1.0477, Train Accuracy: 0.8728, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7972/10000, Train Loss: 1.0582, Train Accuracy: 0.8493, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7973/10000, Train Loss: 1.0596, Train Accuracy: 0.8471, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7974/10000, Train Loss: 1.0623, Train Accuracy: 0.8482, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7975/10000, Train Loss: 1.0578, Train Accuracy: 0.8527, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7976/10000, Train Loss: 1.0636, Train Accuracy: 0.8516, Val Loss: 1.1802, Val Accuracy: 0.7321 Epoch 7977/10000, Train Loss: 1.0727, Train Accuracy: 0.8393, Val Loss: 1.1805, Val Accuracy: 0.7321 Epoch 7978/10000, Train Loss: 1.0673, Train Accuracy: 0.8426, Val Loss: 1.1808, Val Accuracy: 0.7321 Epoch 7979/10000, Train Loss: 1.0672, Train Accuracy: 0.8371, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7980/10000, Train Loss: 1.0583, Train Accuracy: 0.8583, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7981/10000, Train Loss: 1.0630, Train Accuracy: 0.8460, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7982/10000, Train Loss: 1.0630, Train Accuracy: 0.8504, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7983/10000, Train Loss: 1.0714, Train Accuracy: 0.8415, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7984/10000, Train Loss: 1.0479, Train Accuracy: 0.8650, Val Loss: 1.1809, Val Accuracy: 0.7277 Epoch 7985/10000, Train Loss: 1.0642, Train Accuracy: 0.8527, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7986/10000, Train Loss: 1.0585, Train Accuracy: 0.8404, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7987/10000, Train Loss: 1.0603, Train Accuracy: 0.8516, Val Loss: 1.1810, Val Accuracy: 0.7277 Epoch 7988/10000, Train Loss: 1.0729, Train Accuracy: 0.8404, Val Loss: 1.1808, Val Accuracy: 0.7277 Epoch 7989/10000, Train Loss: 1.0695, Train Accuracy: 0.8449, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 7990/10000, Train Loss: 1.0642, Train Accuracy: 0.8504, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7991/10000, Train Loss: 1.0690, Train Accuracy: 0.8449, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7992/10000, Train Loss: 1.0545, Train Accuracy: 0.8616, Val Loss: 1.1806, Val Accuracy: 0.7321 Epoch 7993/10000, Train Loss: 1.0656, Train Accuracy: 0.8504, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7994/10000, Train Loss: 1.0651, Train Accuracy: 0.8493, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 7995/10000, Train Loss: 1.0707, Train Accuracy: 0.8393, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 7996/10000, Train Loss: 1.0575, Train Accuracy: 0.8538, Val Loss: 1.1800, Val Accuracy: 0.7321 Epoch 7997/10000, Train Loss: 1.0648, Train Accuracy: 0.8471, Val Loss: 1.1801, Val Accuracy: 0.7321 Epoch 7998/10000, Train Loss: 1.0704, Train Accuracy: 0.8415, Val Loss: 1.1801, Val Accuracy: 0.7321 Epoch 7999/10000, Train Loss: 1.0532, Train Accuracy: 0.8616, Val Loss: 1.1801, Val Accuracy: 0.7321 Epoch 8000/10000, Train Loss: 1.0541, Train Accuracy: 0.8571, Val Loss: 1.1803, Val Accuracy: 0.7321 Epoch 8001/10000, Train Loss: 1.0528, Train Accuracy: 0.8594, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 8002/10000, Train Loss: 1.0569, Train Accuracy: 0.8560, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 8003/10000, Train Loss: 1.0570, Train Accuracy: 0.8616, Val Loss: 1.1804, Val Accuracy: 0.7321 Epoch 8004/10000, Train Loss: 1.0562, Train Accuracy: 0.8583, Val Loss: 1.1805, Val Accuracy: 0.7277 Epoch 8005/10000, Train Loss: 1.0577, Train Accuracy: 0.8583, Val Loss: 1.1804, Val Accuracy: 0.7277 Epoch 8006/10000, Train Loss: 1.0654, Train Accuracy: 0.8471, Val Loss: 1.1802, Val Accuracy: 0.7277 Epoch 8007/10000, Train Loss: 1.0611, Train Accuracy: 0.8449, Val Loss: 1.1800, Val Accuracy: 0.7321 Epoch 8008/10000, Train Loss: 1.0714, Train Accuracy: 0.8438, Val Loss: 1.1800, Val Accuracy: 0.7277 Epoch 8009/10000, Train Loss: 1.0578, Train Accuracy: 0.8538, Val Loss: 1.1799, Val Accuracy: 0.7321 Epoch 8010/10000, Train Loss: 1.0678, Train Accuracy: 0.8460, Val Loss: 1.1801, Val Accuracy: 0.7321 Epoch 8011/10000, Train Loss: 1.0623, Train Accuracy: 0.8516, Val Loss: 1.1801, Val Accuracy: 0.7277 Epoch 8012/10000, Train Loss: 1.0620, Train Accuracy: 0.8471, Val Loss: 1.1800, Val Accuracy: 0.7321 Epoch 8013/10000, Train Loss: 1.0522, Train Accuracy: 0.8549, Val Loss: 1.1799, Val Accuracy: 0.7366 Epoch 8014/10000, Train Loss: 1.0707, Train Accuracy: 0.8393, Val Loss: 1.1797, Val Accuracy: 0.7321 Epoch 8015/10000, Train Loss: 1.0595, Train Accuracy: 0.8438, Val Loss: 1.1795, Val Accuracy: 0.7366 Epoch 8016/10000, Train Loss: 1.0537, Train Accuracy: 0.8594, Val Loss: 1.1796, Val Accuracy: 0.7321 Epoch 8017/10000, Train Loss: 1.0660, Train Accuracy: 0.8516, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8018/10000, Train Loss: 1.0587, Train Accuracy: 0.8527, Val Loss: 1.1795, Val Accuracy: 0.7321 Epoch 8019/10000, Train Loss: 1.0683, Train Accuracy: 0.8460, Val Loss: 1.1794, Val Accuracy: 0.7321 Epoch 8020/10000, Train Loss: 1.0714, Train Accuracy: 0.8438, Val Loss: 1.1794, Val Accuracy: 0.7366 Epoch 8021/10000, Train Loss: 1.0726, Train Accuracy: 0.8404, Val Loss: 1.1793, Val Accuracy: 0.7366 Epoch 8022/10000, Train Loss: 1.0561, Train Accuracy: 0.8616, Val Loss: 1.1796, Val Accuracy: 0.7321 Epoch 8023/10000, Train Loss: 1.0700, Train Accuracy: 0.8415, Val Loss: 1.1794, Val Accuracy: 0.7321 Epoch 8024/10000, Train Loss: 1.0486, Train Accuracy: 0.8705, Val Loss: 1.1795, Val Accuracy: 0.7321 Epoch 8025/10000, Train Loss: 1.0667, Train Accuracy: 0.8449, Val Loss: 1.1796, Val Accuracy: 0.7366 Epoch 8026/10000, Train Loss: 1.0494, Train Accuracy: 0.8627, Val Loss: 1.1793, Val Accuracy: 0.7366 Epoch 8027/10000, Train Loss: 1.0607, Train Accuracy: 0.8438, Val Loss: 1.1794, Val Accuracy: 0.7366 Epoch 8028/10000, Train Loss: 1.0508, Train Accuracy: 0.8583, Val Loss: 1.1793, Val Accuracy: 0.7366 Epoch 8029/10000, Train Loss: 1.0612, Train Accuracy: 0.8516, Val Loss: 1.1793, Val Accuracy: 0.7366 Epoch 8030/10000, Train Loss: 1.0551, Train Accuracy: 0.8594, Val Loss: 1.1795, Val Accuracy: 0.7366 Epoch 8031/10000, Train Loss: 1.0541, Train Accuracy: 0.8627, Val Loss: 1.1796, Val Accuracy: 0.7366 Epoch 8032/10000, Train Loss: 1.0641, Train Accuracy: 0.8471, Val Loss: 1.1796, Val Accuracy: 0.7321 Epoch 8033/10000, Train Loss: 1.0631, Train Accuracy: 0.8438, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8034/10000, Train Loss: 1.0673, Train Accuracy: 0.8449, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8035/10000, Train Loss: 1.0615, Train Accuracy: 0.8504, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8036/10000, Train Loss: 1.0519, Train Accuracy: 0.8538, Val Loss: 1.1791, Val Accuracy: 0.7366 Epoch 8037/10000, Train Loss: 1.0613, Train Accuracy: 0.8516, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8038/10000, Train Loss: 1.0575, Train Accuracy: 0.8516, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8039/10000, Train Loss: 1.0600, Train Accuracy: 0.8583, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8040/10000, Train Loss: 1.0653, Train Accuracy: 0.8415, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8041/10000, Train Loss: 1.0563, Train Accuracy: 0.8594, Val Loss: 1.1787, Val Accuracy: 0.7321 Epoch 8042/10000, Train Loss: 1.0515, Train Accuracy: 0.8549, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8043/10000, Train Loss: 1.0510, Train Accuracy: 0.8583, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8044/10000, Train Loss: 1.0775, Train Accuracy: 0.8382, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8045/10000, Train Loss: 1.0603, Train Accuracy: 0.8482, Val Loss: 1.1788, Val Accuracy: 0.7321 Epoch 8046/10000, Train Loss: 1.0647, Train Accuracy: 0.8438, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8047/10000, Train Loss: 1.0541, Train Accuracy: 0.8583, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8048/10000, Train Loss: 1.0444, Train Accuracy: 0.8683, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8049/10000, Train Loss: 1.0594, Train Accuracy: 0.8504, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8050/10000, Train Loss: 1.0520, Train Accuracy: 0.8661, Val Loss: 1.1790, Val Accuracy: 0.7366 Epoch 8051/10000, Train Loss: 1.0589, Train Accuracy: 0.8571, Val Loss: 1.1790, Val Accuracy: 0.7366 Epoch 8052/10000, Train Loss: 1.0534, Train Accuracy: 0.8594, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8053/10000, Train Loss: 1.0635, Train Accuracy: 0.8471, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8054/10000, Train Loss: 1.0656, Train Accuracy: 0.8471, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8055/10000, Train Loss: 1.0570, Train Accuracy: 0.8583, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8056/10000, Train Loss: 1.0648, Train Accuracy: 0.8460, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8057/10000, Train Loss: 1.0683, Train Accuracy: 0.8415, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8058/10000, Train Loss: 1.0632, Train Accuracy: 0.8471, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8059/10000, Train Loss: 1.0588, Train Accuracy: 0.8482, Val Loss: 1.1794, Val Accuracy: 0.7366 Epoch 8060/10000, Train Loss: 1.0653, Train Accuracy: 0.8460, Val Loss: 1.1791, Val Accuracy: 0.7366 Epoch 8061/10000, Train Loss: 1.0550, Train Accuracy: 0.8516, Val Loss: 1.1791, Val Accuracy: 0.7366 Epoch 8062/10000, Train Loss: 1.0453, Train Accuracy: 0.8683, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8063/10000, Train Loss: 1.0556, Train Accuracy: 0.8516, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8064/10000, Train Loss: 1.0620, Train Accuracy: 0.8460, Val Loss: 1.1787, Val Accuracy: 0.7366 Epoch 8065/10000, Train Loss: 1.0694, Train Accuracy: 0.8426, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8066/10000, Train Loss: 1.0708, Train Accuracy: 0.8337, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8067/10000, Train Loss: 1.0543, Train Accuracy: 0.8672, Val Loss: 1.1782, Val Accuracy: 0.7366 Epoch 8068/10000, Train Loss: 1.0474, Train Accuracy: 0.8705, Val Loss: 1.1783, Val Accuracy: 0.7366 Epoch 8069/10000, Train Loss: 1.0575, Train Accuracy: 0.8482, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8070/10000, Train Loss: 1.0588, Train Accuracy: 0.8538, Val Loss: 1.1782, Val Accuracy: 0.7366 Epoch 8071/10000, Train Loss: 1.0620, Train Accuracy: 0.8482, Val Loss: 1.1783, Val Accuracy: 0.7366 Epoch 8072/10000, Train Loss: 1.0578, Train Accuracy: 0.8538, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8073/10000, Train Loss: 1.0532, Train Accuracy: 0.8549, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8074/10000, Train Loss: 1.0558, Train Accuracy: 0.8594, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8075/10000, Train Loss: 1.0621, Train Accuracy: 0.8516, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8076/10000, Train Loss: 1.0540, Train Accuracy: 0.8583, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8077/10000, Train Loss: 1.0675, Train Accuracy: 0.8482, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8078/10000, Train Loss: 1.0630, Train Accuracy: 0.8393, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8079/10000, Train Loss: 1.0501, Train Accuracy: 0.8571, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8080/10000, Train Loss: 1.0520, Train Accuracy: 0.8605, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8081/10000, Train Loss: 1.0579, Train Accuracy: 0.8538, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8082/10000, Train Loss: 1.0517, Train Accuracy: 0.8583, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8083/10000, Train Loss: 1.0644, Train Accuracy: 0.8482, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8084/10000, Train Loss: 1.0526, Train Accuracy: 0.8616, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8085/10000, Train Loss: 1.0511, Train Accuracy: 0.8594, Val Loss: 1.1788, Val Accuracy: 0.7321 Epoch 8086/10000, Train Loss: 1.0419, Train Accuracy: 0.8705, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8087/10000, Train Loss: 1.0599, Train Accuracy: 0.8516, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8088/10000, Train Loss: 1.0640, Train Accuracy: 0.8538, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8089/10000, Train Loss: 1.0485, Train Accuracy: 0.8717, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8090/10000, Train Loss: 1.0582, Train Accuracy: 0.8583, Val Loss: 1.1786, Val Accuracy: 0.7321 Epoch 8091/10000, Train Loss: 1.0611, Train Accuracy: 0.8538, Val Loss: 1.1787, Val Accuracy: 0.7321 Epoch 8092/10000, Train Loss: 1.0529, Train Accuracy: 0.8583, Val Loss: 1.1791, Val Accuracy: 0.7321 Epoch 8093/10000, Train Loss: 1.0556, Train Accuracy: 0.8560, Val Loss: 1.1788, Val Accuracy: 0.7321 Epoch 8094/10000, Train Loss: 1.0705, Train Accuracy: 0.8404, Val Loss: 1.1791, Val Accuracy: 0.7321 Epoch 8095/10000, Train Loss: 1.0481, Train Accuracy: 0.8638, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8096/10000, Train Loss: 1.0623, Train Accuracy: 0.8516, Val Loss: 1.1789, Val Accuracy: 0.7321 Epoch 8097/10000, Train Loss: 1.0660, Train Accuracy: 0.8482, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8098/10000, Train Loss: 1.0514, Train Accuracy: 0.8650, Val Loss: 1.1791, Val Accuracy: 0.7321 Epoch 8099/10000, Train Loss: 1.0591, Train Accuracy: 0.8516, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8100/10000, Train Loss: 1.0647, Train Accuracy: 0.8415, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8101/10000, Train Loss: 1.0555, Train Accuracy: 0.8549, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8102/10000, Train Loss: 1.0650, Train Accuracy: 0.8482, Val Loss: 1.1796, Val Accuracy: 0.7321 Epoch 8103/10000, Train Loss: 1.0473, Train Accuracy: 0.8650, Val Loss: 1.1795, Val Accuracy: 0.7321 Epoch 8104/10000, Train Loss: 1.0643, Train Accuracy: 0.8471, Val Loss: 1.1795, Val Accuracy: 0.7321 Epoch 8105/10000, Train Loss: 1.0552, Train Accuracy: 0.8605, Val Loss: 1.1795, Val Accuracy: 0.7321 Epoch 8106/10000, Train Loss: 1.0612, Train Accuracy: 0.8493, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8107/10000, Train Loss: 1.0599, Train Accuracy: 0.8571, Val Loss: 1.1791, Val Accuracy: 0.7321 Epoch 8108/10000, Train Loss: 1.0614, Train Accuracy: 0.8504, Val Loss: 1.1795, Val Accuracy: 0.7321 Epoch 8109/10000, Train Loss: 1.0596, Train Accuracy: 0.8460, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8110/10000, Train Loss: 1.0568, Train Accuracy: 0.8583, Val Loss: 1.1793, Val Accuracy: 0.7321 Epoch 8111/10000, Train Loss: 1.0565, Train Accuracy: 0.8527, Val Loss: 1.1792, Val Accuracy: 0.7321 Epoch 8112/10000, Train Loss: 1.0605, Train Accuracy: 0.8482, Val Loss: 1.1791, Val Accuracy: 0.7321 Epoch 8113/10000, Train Loss: 1.0602, Train Accuracy: 0.8527, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8114/10000, Train Loss: 1.0582, Train Accuracy: 0.8571, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8115/10000, Train Loss: 1.0631, Train Accuracy: 0.8549, Val Loss: 1.1791, Val Accuracy: 0.7321 Epoch 8116/10000, Train Loss: 1.0564, Train Accuracy: 0.8583, Val Loss: 1.1788, Val Accuracy: 0.7321 Epoch 8117/10000, Train Loss: 1.0480, Train Accuracy: 0.8650, Val Loss: 1.1788, Val Accuracy: 0.7321 Epoch 8118/10000, Train Loss: 1.0674, Train Accuracy: 0.8426, Val Loss: 1.1788, Val Accuracy: 0.7321 Epoch 8119/10000, Train Loss: 1.0652, Train Accuracy: 0.8449, Val Loss: 1.1786, Val Accuracy: 0.7321 Epoch 8120/10000, Train Loss: 1.0757, Train Accuracy: 0.8315, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8121/10000, Train Loss: 1.0637, Train Accuracy: 0.8493, Val Loss: 1.1787, Val Accuracy: 0.7321 Epoch 8122/10000, Train Loss: 1.0681, Train Accuracy: 0.8504, Val Loss: 1.1787, Val Accuracy: 0.7366 Epoch 8123/10000, Train Loss: 1.0551, Train Accuracy: 0.8583, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8124/10000, Train Loss: 1.0429, Train Accuracy: 0.8761, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8125/10000, Train Loss: 1.0618, Train Accuracy: 0.8560, Val Loss: 1.1790, Val Accuracy: 0.7366 Epoch 8126/10000, Train Loss: 1.0563, Train Accuracy: 0.8482, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8127/10000, Train Loss: 1.0550, Train Accuracy: 0.8627, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8128/10000, Train Loss: 1.0575, Train Accuracy: 0.8616, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8129/10000, Train Loss: 1.0594, Train Accuracy: 0.8493, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8130/10000, Train Loss: 1.0526, Train Accuracy: 0.8594, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8131/10000, Train Loss: 1.0440, Train Accuracy: 0.8672, Val Loss: 1.1794, Val Accuracy: 0.7366 Epoch 8132/10000, Train Loss: 1.0605, Train Accuracy: 0.8516, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8133/10000, Train Loss: 1.0492, Train Accuracy: 0.8650, Val Loss: 1.1792, Val Accuracy: 0.7366 Epoch 8134/10000, Train Loss: 1.0457, Train Accuracy: 0.8739, Val Loss: 1.1790, Val Accuracy: 0.7411 Epoch 8135/10000, Train Loss: 1.0535, Train Accuracy: 0.8583, Val Loss: 1.1790, Val Accuracy: 0.7321 Epoch 8136/10000, Train Loss: 1.0691, Train Accuracy: 0.8482, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8137/10000, Train Loss: 1.0491, Train Accuracy: 0.8683, Val Loss: 1.1791, Val Accuracy: 0.7366 Epoch 8138/10000, Train Loss: 1.0670, Train Accuracy: 0.8415, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8139/10000, Train Loss: 1.0629, Train Accuracy: 0.8438, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8140/10000, Train Loss: 1.0543, Train Accuracy: 0.8538, Val Loss: 1.1787, Val Accuracy: 0.7366 Epoch 8141/10000, Train Loss: 1.0586, Train Accuracy: 0.8560, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8142/10000, Train Loss: 1.0593, Train Accuracy: 0.8560, Val Loss: 1.1791, Val Accuracy: 0.7366 Epoch 8143/10000, Train Loss: 1.0687, Train Accuracy: 0.8471, Val Loss: 1.1791, Val Accuracy: 0.7366 Epoch 8144/10000, Train Loss: 1.0595, Train Accuracy: 0.8538, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8145/10000, Train Loss: 1.0558, Train Accuracy: 0.8583, Val Loss: 1.1789, Val Accuracy: 0.7366 Epoch 8146/10000, Train Loss: 1.0499, Train Accuracy: 0.8672, Val Loss: 1.1784, Val Accuracy: 0.7411 Epoch 8147/10000, Train Loss: 1.0644, Train Accuracy: 0.8460, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8148/10000, Train Loss: 1.0537, Train Accuracy: 0.8638, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8149/10000, Train Loss: 1.0486, Train Accuracy: 0.8728, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8150/10000, Train Loss: 1.0473, Train Accuracy: 0.8694, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8151/10000, Train Loss: 1.0654, Train Accuracy: 0.8460, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8152/10000, Train Loss: 1.0557, Train Accuracy: 0.8583, Val Loss: 1.1783, Val Accuracy: 0.7411 Epoch 8153/10000, Train Loss: 1.0453, Train Accuracy: 0.8728, Val Loss: 1.1780, Val Accuracy: 0.7411 Epoch 8154/10000, Train Loss: 1.0501, Train Accuracy: 0.8694, Val Loss: 1.1777, Val Accuracy: 0.7411 Epoch 8155/10000, Train Loss: 1.0512, Train Accuracy: 0.8616, Val Loss: 1.1780, Val Accuracy: 0.7411 Epoch 8156/10000, Train Loss: 1.0585, Train Accuracy: 0.8516, Val Loss: 1.1781, Val Accuracy: 0.7366 Epoch 8157/10000, Train Loss: 1.0624, Train Accuracy: 0.8404, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8158/10000, Train Loss: 1.0526, Train Accuracy: 0.8638, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8159/10000, Train Loss: 1.0543, Train Accuracy: 0.8672, Val Loss: 1.1778, Val Accuracy: 0.7366 Epoch 8160/10000, Train Loss: 1.0669, Train Accuracy: 0.8359, Val Loss: 1.1774, Val Accuracy: 0.7366 Epoch 8161/10000, Train Loss: 1.0753, Train Accuracy: 0.8292, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8162/10000, Train Loss: 1.0624, Train Accuracy: 0.8538, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8163/10000, Train Loss: 1.0624, Train Accuracy: 0.8504, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8164/10000, Train Loss: 1.0595, Train Accuracy: 0.8482, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8165/10000, Train Loss: 1.0571, Train Accuracy: 0.8538, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8166/10000, Train Loss: 1.0606, Train Accuracy: 0.8471, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8167/10000, Train Loss: 1.0460, Train Accuracy: 0.8605, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8168/10000, Train Loss: 1.0598, Train Accuracy: 0.8538, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8169/10000, Train Loss: 1.0601, Train Accuracy: 0.8460, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8170/10000, Train Loss: 1.0583, Train Accuracy: 0.8438, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8171/10000, Train Loss: 1.0538, Train Accuracy: 0.8516, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8172/10000, Train Loss: 1.0376, Train Accuracy: 0.8717, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8173/10000, Train Loss: 1.0607, Train Accuracy: 0.8538, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8174/10000, Train Loss: 1.0505, Train Accuracy: 0.8616, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8175/10000, Train Loss: 1.0506, Train Accuracy: 0.8661, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8176/10000, Train Loss: 1.0555, Train Accuracy: 0.8571, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8177/10000, Train Loss: 1.0625, Train Accuracy: 0.8471, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8178/10000, Train Loss: 1.0659, Train Accuracy: 0.8460, Val Loss: 1.1768, Val Accuracy: 0.7411 Epoch 8179/10000, Train Loss: 1.0660, Train Accuracy: 0.8415, Val Loss: 1.1770, Val Accuracy: 0.7411 Epoch 8180/10000, Train Loss: 1.0612, Train Accuracy: 0.8538, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8181/10000, Train Loss: 1.0571, Train Accuracy: 0.8549, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8182/10000, Train Loss: 1.0666, Train Accuracy: 0.8404, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8183/10000, Train Loss: 1.0557, Train Accuracy: 0.8538, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8184/10000, Train Loss: 1.0524, Train Accuracy: 0.8694, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8185/10000, Train Loss: 1.0664, Train Accuracy: 0.8449, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8186/10000, Train Loss: 1.0469, Train Accuracy: 0.8594, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8187/10000, Train Loss: 1.0672, Train Accuracy: 0.8359, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8188/10000, Train Loss: 1.0515, Train Accuracy: 0.8571, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8189/10000, Train Loss: 1.0675, Train Accuracy: 0.8393, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8190/10000, Train Loss: 1.0573, Train Accuracy: 0.8571, Val Loss: 1.1776, Val Accuracy: 0.7366 Epoch 8191/10000, Train Loss: 1.0504, Train Accuracy: 0.8571, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8192/10000, Train Loss: 1.0598, Train Accuracy: 0.8504, Val Loss: 1.1776, Val Accuracy: 0.7366 Epoch 8193/10000, Train Loss: 1.0516, Train Accuracy: 0.8594, Val Loss: 1.1774, Val Accuracy: 0.7366 Epoch 8194/10000, Train Loss: 1.0572, Train Accuracy: 0.8527, Val Loss: 1.1776, Val Accuracy: 0.7366 Epoch 8195/10000, Train Loss: 1.0541, Train Accuracy: 0.8538, Val Loss: 1.1776, Val Accuracy: 0.7366 Epoch 8196/10000, Train Loss: 1.0553, Train Accuracy: 0.8571, Val Loss: 1.1776, Val Accuracy: 0.7366 Epoch 8197/10000, Train Loss: 1.0619, Train Accuracy: 0.8493, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8198/10000, Train Loss: 1.0569, Train Accuracy: 0.8516, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8199/10000, Train Loss: 1.0529, Train Accuracy: 0.8627, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8200/10000, Train Loss: 1.0582, Train Accuracy: 0.8560, Val Loss: 1.1778, Val Accuracy: 0.7366 Epoch 8201/10000, Train Loss: 1.0540, Train Accuracy: 0.8616, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8202/10000, Train Loss: 1.0626, Train Accuracy: 0.8560, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8203/10000, Train Loss: 1.0543, Train Accuracy: 0.8627, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8204/10000, Train Loss: 1.0604, Train Accuracy: 0.8493, Val Loss: 1.1781, Val Accuracy: 0.7366 Epoch 8205/10000, Train Loss: 1.0523, Train Accuracy: 0.8605, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8206/10000, Train Loss: 1.0634, Train Accuracy: 0.8504, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8207/10000, Train Loss: 1.0664, Train Accuracy: 0.8382, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8208/10000, Train Loss: 1.0606, Train Accuracy: 0.8583, Val Loss: 1.1778, Val Accuracy: 0.7366 Epoch 8209/10000, Train Loss: 1.0628, Train Accuracy: 0.8404, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8210/10000, Train Loss: 1.0638, Train Accuracy: 0.8516, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8211/10000, Train Loss: 1.0624, Train Accuracy: 0.8504, Val Loss: 1.1781, Val Accuracy: 0.7366 Epoch 8212/10000, Train Loss: 1.0665, Train Accuracy: 0.8460, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8213/10000, Train Loss: 1.0598, Train Accuracy: 0.8538, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8214/10000, Train Loss: 1.0579, Train Accuracy: 0.8594, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8215/10000, Train Loss: 1.0568, Train Accuracy: 0.8538, Val Loss: 1.1782, Val Accuracy: 0.7366 Epoch 8216/10000, Train Loss: 1.0563, Train Accuracy: 0.8549, Val Loss: 1.1783, Val Accuracy: 0.7366 Epoch 8217/10000, Train Loss: 1.0583, Train Accuracy: 0.8504, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8218/10000, Train Loss: 1.0534, Train Accuracy: 0.8571, Val Loss: 1.1784, Val Accuracy: 0.7321 Epoch 8219/10000, Train Loss: 1.0574, Train Accuracy: 0.8471, Val Loss: 1.1783, Val Accuracy: 0.7366 Epoch 8220/10000, Train Loss: 1.0629, Train Accuracy: 0.8449, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8221/10000, Train Loss: 1.0588, Train Accuracy: 0.8583, Val Loss: 1.1782, Val Accuracy: 0.7366 Epoch 8222/10000, Train Loss: 1.0604, Train Accuracy: 0.8504, Val Loss: 1.1781, Val Accuracy: 0.7321 Epoch 8223/10000, Train Loss: 1.0634, Train Accuracy: 0.8426, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8224/10000, Train Loss: 1.0475, Train Accuracy: 0.8661, Val Loss: 1.1778, Val Accuracy: 0.7366 Epoch 8225/10000, Train Loss: 1.0518, Train Accuracy: 0.8627, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8226/10000, Train Loss: 1.0537, Train Accuracy: 0.8549, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8227/10000, Train Loss: 1.0640, Train Accuracy: 0.8504, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8228/10000, Train Loss: 1.0498, Train Accuracy: 0.8605, Val Loss: 1.1781, Val Accuracy: 0.7366 Epoch 8229/10000, Train Loss: 1.0623, Train Accuracy: 0.8549, Val Loss: 1.1783, Val Accuracy: 0.7366 Epoch 8230/10000, Train Loss: 1.0559, Train Accuracy: 0.8638, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8231/10000, Train Loss: 1.0558, Train Accuracy: 0.8605, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8232/10000, Train Loss: 1.0533, Train Accuracy: 0.8627, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8233/10000, Train Loss: 1.0449, Train Accuracy: 0.8694, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8234/10000, Train Loss: 1.0436, Train Accuracy: 0.8616, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8235/10000, Train Loss: 1.0573, Train Accuracy: 0.8516, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8236/10000, Train Loss: 1.0543, Train Accuracy: 0.8594, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8237/10000, Train Loss: 1.0681, Train Accuracy: 0.8449, Val Loss: 1.1787, Val Accuracy: 0.7366 Epoch 8238/10000, Train Loss: 1.0566, Train Accuracy: 0.8571, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8239/10000, Train Loss: 1.0624, Train Accuracy: 0.8471, Val Loss: 1.1788, Val Accuracy: 0.7366 Epoch 8240/10000, Train Loss: 1.0501, Train Accuracy: 0.8638, Val Loss: 1.1786, Val Accuracy: 0.7366 Epoch 8241/10000, Train Loss: 1.0479, Train Accuracy: 0.8661, Val Loss: 1.1785, Val Accuracy: 0.7366 Epoch 8242/10000, Train Loss: 1.0620, Train Accuracy: 0.8527, Val Loss: 1.1784, Val Accuracy: 0.7366 Epoch 8243/10000, Train Loss: 1.0565, Train Accuracy: 0.8538, Val Loss: 1.1783, Val Accuracy: 0.7366 Epoch 8244/10000, Train Loss: 1.0438, Train Accuracy: 0.8705, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8245/10000, Train Loss: 1.0532, Train Accuracy: 0.8560, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8246/10000, Train Loss: 1.0572, Train Accuracy: 0.8560, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8247/10000, Train Loss: 1.0576, Train Accuracy: 0.8493, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8248/10000, Train Loss: 1.0468, Train Accuracy: 0.8661, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8249/10000, Train Loss: 1.0538, Train Accuracy: 0.8583, Val Loss: 1.1781, Val Accuracy: 0.7366 Epoch 8250/10000, Train Loss: 1.0589, Train Accuracy: 0.8516, Val Loss: 1.1780, Val Accuracy: 0.7366 Epoch 8251/10000, Train Loss: 1.0467, Train Accuracy: 0.8694, Val Loss: 1.1779, Val Accuracy: 0.7366 Epoch 8252/10000, Train Loss: 1.0459, Train Accuracy: 0.8672, Val Loss: 1.1780, Val Accuracy: 0.7411 Epoch 8253/10000, Train Loss: 1.0560, Train Accuracy: 0.8583, Val Loss: 1.1784, Val Accuracy: 0.7411 Epoch 8254/10000, Train Loss: 1.0561, Train Accuracy: 0.8538, Val Loss: 1.1785, Val Accuracy: 0.7411 Epoch 8255/10000, Train Loss: 1.0662, Train Accuracy: 0.8538, Val Loss: 1.1785, Val Accuracy: 0.7411 Epoch 8256/10000, Train Loss: 1.0646, Train Accuracy: 0.8404, Val Loss: 1.1784, Val Accuracy: 0.7411 Epoch 8257/10000, Train Loss: 1.0610, Train Accuracy: 0.8560, Val Loss: 1.1781, Val Accuracy: 0.7411 Epoch 8258/10000, Train Loss: 1.0377, Train Accuracy: 0.8772, Val Loss: 1.1780, Val Accuracy: 0.7411 Epoch 8259/10000, Train Loss: 1.0531, Train Accuracy: 0.8605, Val Loss: 1.1780, Val Accuracy: 0.7411 Epoch 8260/10000, Train Loss: 1.0629, Train Accuracy: 0.8560, Val Loss: 1.1776, Val Accuracy: 0.7411 Epoch 8261/10000, Train Loss: 1.0506, Train Accuracy: 0.8616, Val Loss: 1.1775, Val Accuracy: 0.7411 Epoch 8262/10000, Train Loss: 1.0611, Train Accuracy: 0.8482, Val Loss: 1.1776, Val Accuracy: 0.7411 Epoch 8263/10000, Train Loss: 1.0545, Train Accuracy: 0.8571, Val Loss: 1.1777, Val Accuracy: 0.7411 Epoch 8264/10000, Train Loss: 1.0584, Train Accuracy: 0.8504, Val Loss: 1.1775, Val Accuracy: 0.7411 Epoch 8265/10000, Train Loss: 1.0427, Train Accuracy: 0.8694, Val Loss: 1.1775, Val Accuracy: 0.7411 Epoch 8266/10000, Train Loss: 1.0500, Train Accuracy: 0.8627, Val Loss: 1.1775, Val Accuracy: 0.7411 Epoch 8267/10000, Train Loss: 1.0437, Train Accuracy: 0.8705, Val Loss: 1.1775, Val Accuracy: 0.7411 Epoch 8268/10000, Train Loss: 1.0410, Train Accuracy: 0.8705, Val Loss: 1.1776, Val Accuracy: 0.7411 Epoch 8269/10000, Train Loss: 1.0564, Train Accuracy: 0.8504, Val Loss: 1.1774, Val Accuracy: 0.7411 Epoch 8270/10000, Train Loss: 1.0520, Train Accuracy: 0.8705, Val Loss: 1.1773, Val Accuracy: 0.7411 Epoch 8271/10000, Train Loss: 1.0531, Train Accuracy: 0.8538, Val Loss: 1.1774, Val Accuracy: 0.7411 Epoch 8272/10000, Train Loss: 1.0522, Train Accuracy: 0.8616, Val Loss: 1.1773, Val Accuracy: 0.7411 Epoch 8273/10000, Train Loss: 1.0495, Train Accuracy: 0.8638, Val Loss: 1.1773, Val Accuracy: 0.7411 Epoch 8274/10000, Train Loss: 1.0592, Train Accuracy: 0.8527, Val Loss: 1.1773, Val Accuracy: 0.7411 Epoch 8275/10000, Train Loss: 1.0540, Train Accuracy: 0.8571, Val Loss: 1.1775, Val Accuracy: 0.7411 Epoch 8276/10000, Train Loss: 1.0596, Train Accuracy: 0.8460, Val Loss: 1.1774, Val Accuracy: 0.7411 Epoch 8277/10000, Train Loss: 1.0667, Train Accuracy: 0.8493, Val Loss: 1.1772, Val Accuracy: 0.7411 Epoch 8278/10000, Train Loss: 1.0520, Train Accuracy: 0.8560, Val Loss: 1.1771, Val Accuracy: 0.7411 Epoch 8279/10000, Train Loss: 1.0657, Train Accuracy: 0.8382, Val Loss: 1.1770, Val Accuracy: 0.7411 Epoch 8280/10000, Train Loss: 1.0525, Train Accuracy: 0.8594, Val Loss: 1.1770, Val Accuracy: 0.7411 Epoch 8281/10000, Train Loss: 1.0587, Train Accuracy: 0.8482, Val Loss: 1.1767, Val Accuracy: 0.7411 Epoch 8282/10000, Train Loss: 1.0601, Train Accuracy: 0.8549, Val Loss: 1.1768, Val Accuracy: 0.7411 Epoch 8283/10000, Train Loss: 1.0517, Train Accuracy: 0.8560, Val Loss: 1.1768, Val Accuracy: 0.7411 Epoch 8284/10000, Train Loss: 1.0579, Train Accuracy: 0.8583, Val Loss: 1.1767, Val Accuracy: 0.7411 Epoch 8285/10000, Train Loss: 1.0510, Train Accuracy: 0.8638, Val Loss: 1.1768, Val Accuracy: 0.7411 Epoch 8286/10000, Train Loss: 1.0563, Train Accuracy: 0.8583, Val Loss: 1.1766, Val Accuracy: 0.7411 Epoch 8287/10000, Train Loss: 1.0534, Train Accuracy: 0.8627, Val Loss: 1.1766, Val Accuracy: 0.7411 Epoch 8288/10000, Train Loss: 1.0479, Train Accuracy: 0.8650, Val Loss: 1.1767, Val Accuracy: 0.7411 Epoch 8289/10000, Train Loss: 1.0534, Train Accuracy: 0.8583, Val Loss: 1.1769, Val Accuracy: 0.7411 Epoch 8290/10000, Train Loss: 1.0548, Train Accuracy: 0.8627, Val Loss: 1.1767, Val Accuracy: 0.7411 Epoch 8291/10000, Train Loss: 1.0491, Train Accuracy: 0.8694, Val Loss: 1.1768, Val Accuracy: 0.7411 Epoch 8292/10000, Train Loss: 1.0479, Train Accuracy: 0.8650, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8293/10000, Train Loss: 1.0470, Train Accuracy: 0.8650, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8294/10000, Train Loss: 1.0471, Train Accuracy: 0.8661, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8295/10000, Train Loss: 1.0584, Train Accuracy: 0.8616, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8296/10000, Train Loss: 1.0617, Train Accuracy: 0.8538, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8297/10000, Train Loss: 1.0542, Train Accuracy: 0.8638, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8298/10000, Train Loss: 1.0571, Train Accuracy: 0.8605, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8299/10000, Train Loss: 1.0537, Train Accuracy: 0.8560, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8300/10000, Train Loss: 1.0579, Train Accuracy: 0.8549, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8301/10000, Train Loss: 1.0487, Train Accuracy: 0.8627, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8302/10000, Train Loss: 1.0488, Train Accuracy: 0.8638, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8303/10000, Train Loss: 1.0532, Train Accuracy: 0.8616, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8304/10000, Train Loss: 1.0580, Train Accuracy: 0.8538, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8305/10000, Train Loss: 1.0467, Train Accuracy: 0.8672, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8306/10000, Train Loss: 1.0478, Train Accuracy: 0.8638, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8307/10000, Train Loss: 1.0447, Train Accuracy: 0.8750, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8308/10000, Train Loss: 1.0521, Train Accuracy: 0.8594, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8309/10000, Train Loss: 1.0489, Train Accuracy: 0.8672, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8310/10000, Train Loss: 1.0561, Train Accuracy: 0.8560, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8311/10000, Train Loss: 1.0449, Train Accuracy: 0.8728, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8312/10000, Train Loss: 1.0490, Train Accuracy: 0.8594, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8313/10000, Train Loss: 1.0555, Train Accuracy: 0.8560, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8314/10000, Train Loss: 1.0582, Train Accuracy: 0.8560, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8315/10000, Train Loss: 1.0489, Train Accuracy: 0.8717, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8316/10000, Train Loss: 1.0454, Train Accuracy: 0.8661, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8317/10000, Train Loss: 1.0514, Train Accuracy: 0.8661, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8318/10000, Train Loss: 1.0555, Train Accuracy: 0.8583, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8319/10000, Train Loss: 1.0429, Train Accuracy: 0.8638, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8320/10000, Train Loss: 1.0677, Train Accuracy: 0.8449, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8321/10000, Train Loss: 1.0558, Train Accuracy: 0.8527, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8322/10000, Train Loss: 1.0546, Train Accuracy: 0.8638, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8323/10000, Train Loss: 1.0564, Train Accuracy: 0.8583, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8324/10000, Train Loss: 1.0376, Train Accuracy: 0.8772, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8325/10000, Train Loss: 1.0629, Train Accuracy: 0.8493, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8326/10000, Train Loss: 1.0520, Train Accuracy: 0.8571, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8327/10000, Train Loss: 1.0671, Train Accuracy: 0.8359, Val Loss: 1.1774, Val Accuracy: 0.7366 Epoch 8328/10000, Train Loss: 1.0612, Train Accuracy: 0.8504, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8329/10000, Train Loss: 1.0499, Train Accuracy: 0.8661, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8330/10000, Train Loss: 1.0505, Train Accuracy: 0.8605, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8331/10000, Train Loss: 1.0507, Train Accuracy: 0.8627, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8332/10000, Train Loss: 1.0387, Train Accuracy: 0.8728, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8333/10000, Train Loss: 1.0568, Train Accuracy: 0.8583, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8334/10000, Train Loss: 1.0482, Train Accuracy: 0.8661, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8335/10000, Train Loss: 1.0598, Train Accuracy: 0.8527, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8336/10000, Train Loss: 1.0594, Train Accuracy: 0.8493, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8337/10000, Train Loss: 1.0586, Train Accuracy: 0.8549, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8338/10000, Train Loss: 1.0571, Train Accuracy: 0.8583, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8339/10000, Train Loss: 1.0503, Train Accuracy: 0.8594, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8340/10000, Train Loss: 1.0576, Train Accuracy: 0.8560, Val Loss: 1.1762, Val Accuracy: 0.7411 Epoch 8341/10000, Train Loss: 1.0463, Train Accuracy: 0.8560, Val Loss: 1.1762, Val Accuracy: 0.7411 Epoch 8342/10000, Train Loss: 1.0524, Train Accuracy: 0.8594, Val Loss: 1.1764, Val Accuracy: 0.7411 Epoch 8343/10000, Train Loss: 1.0494, Train Accuracy: 0.8538, Val Loss: 1.1763, Val Accuracy: 0.7411 Epoch 8344/10000, Train Loss: 1.0517, Train Accuracy: 0.8549, Val Loss: 1.1764, Val Accuracy: 0.7411 Epoch 8345/10000, Train Loss: 1.0580, Train Accuracy: 0.8504, Val Loss: 1.1761, Val Accuracy: 0.7411 Epoch 8346/10000, Train Loss: 1.0494, Train Accuracy: 0.8616, Val Loss: 1.1758, Val Accuracy: 0.7411 Epoch 8347/10000, Train Loss: 1.0556, Train Accuracy: 0.8605, Val Loss: 1.1758, Val Accuracy: 0.7411 Epoch 8348/10000, Train Loss: 1.0558, Train Accuracy: 0.8571, Val Loss: 1.1756, Val Accuracy: 0.7411 Epoch 8349/10000, Train Loss: 1.0637, Train Accuracy: 0.8382, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 8350/10000, Train Loss: 1.0523, Train Accuracy: 0.8527, Val Loss: 1.1756, Val Accuracy: 0.7411 Epoch 8351/10000, Train Loss: 1.0471, Train Accuracy: 0.8694, Val Loss: 1.1758, Val Accuracy: 0.7411 Epoch 8352/10000, Train Loss: 1.0577, Train Accuracy: 0.8504, Val Loss: 1.1756, Val Accuracy: 0.7411 Epoch 8353/10000, Train Loss: 1.0542, Train Accuracy: 0.8638, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8354/10000, Train Loss: 1.0437, Train Accuracy: 0.8672, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8355/10000, Train Loss: 1.0548, Train Accuracy: 0.8627, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8356/10000, Train Loss: 1.0537, Train Accuracy: 0.8560, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8357/10000, Train Loss: 1.0371, Train Accuracy: 0.8783, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8358/10000, Train Loss: 1.0478, Train Accuracy: 0.8717, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8359/10000, Train Loss: 1.0554, Train Accuracy: 0.8527, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8360/10000, Train Loss: 1.0597, Train Accuracy: 0.8493, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8361/10000, Train Loss: 1.0522, Train Accuracy: 0.8560, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8362/10000, Train Loss: 1.0517, Train Accuracy: 0.8594, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8363/10000, Train Loss: 1.0571, Train Accuracy: 0.8594, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8364/10000, Train Loss: 1.0579, Train Accuracy: 0.8516, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8365/10000, Train Loss: 1.0482, Train Accuracy: 0.8650, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8366/10000, Train Loss: 1.0533, Train Accuracy: 0.8560, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8367/10000, Train Loss: 1.0467, Train Accuracy: 0.8694, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8368/10000, Train Loss: 1.0491, Train Accuracy: 0.8650, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8369/10000, Train Loss: 1.0636, Train Accuracy: 0.8471, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8370/10000, Train Loss: 1.0387, Train Accuracy: 0.8739, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8371/10000, Train Loss: 1.0460, Train Accuracy: 0.8694, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8372/10000, Train Loss: 1.0584, Train Accuracy: 0.8504, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8373/10000, Train Loss: 1.0499, Train Accuracy: 0.8583, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8374/10000, Train Loss: 1.0415, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7411 Epoch 8375/10000, Train Loss: 1.0446, Train Accuracy: 0.8683, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8376/10000, Train Loss: 1.0505, Train Accuracy: 0.8661, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8377/10000, Train Loss: 1.0549, Train Accuracy: 0.8594, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8378/10000, Train Loss: 1.0613, Train Accuracy: 0.8504, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8379/10000, Train Loss: 1.0546, Train Accuracy: 0.8571, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8380/10000, Train Loss: 1.0579, Train Accuracy: 0.8527, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8381/10000, Train Loss: 1.0449, Train Accuracy: 0.8694, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8382/10000, Train Loss: 1.0542, Train Accuracy: 0.8605, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8383/10000, Train Loss: 1.0483, Train Accuracy: 0.8650, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8384/10000, Train Loss: 1.0614, Train Accuracy: 0.8549, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8385/10000, Train Loss: 1.0522, Train Accuracy: 0.8583, Val Loss: 1.1762, Val Accuracy: 0.7411 Epoch 8386/10000, Train Loss: 1.0519, Train Accuracy: 0.8560, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8387/10000, Train Loss: 1.0469, Train Accuracy: 0.8616, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8388/10000, Train Loss: 1.0439, Train Accuracy: 0.8705, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8389/10000, Train Loss: 1.0486, Train Accuracy: 0.8672, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8390/10000, Train Loss: 1.0530, Train Accuracy: 0.8616, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8391/10000, Train Loss: 1.0515, Train Accuracy: 0.8661, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8392/10000, Train Loss: 1.0414, Train Accuracy: 0.8750, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8393/10000, Train Loss: 1.0505, Train Accuracy: 0.8605, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8394/10000, Train Loss: 1.0407, Train Accuracy: 0.8705, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8395/10000, Train Loss: 1.0442, Train Accuracy: 0.8661, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8396/10000, Train Loss: 1.0517, Train Accuracy: 0.8638, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8397/10000, Train Loss: 1.0528, Train Accuracy: 0.8583, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8398/10000, Train Loss: 1.0589, Train Accuracy: 0.8504, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8399/10000, Train Loss: 1.0540, Train Accuracy: 0.8605, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8400/10000, Train Loss: 1.0514, Train Accuracy: 0.8616, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8401/10000, Train Loss: 1.0521, Train Accuracy: 0.8594, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8402/10000, Train Loss: 1.0402, Train Accuracy: 0.8739, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8403/10000, Train Loss: 1.0606, Train Accuracy: 0.8504, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 8404/10000, Train Loss: 1.0420, Train Accuracy: 0.8761, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 8405/10000, Train Loss: 1.0561, Train Accuracy: 0.8605, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8406/10000, Train Loss: 1.0539, Train Accuracy: 0.8616, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8407/10000, Train Loss: 1.0534, Train Accuracy: 0.8538, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8408/10000, Train Loss: 1.0513, Train Accuracy: 0.8627, Val Loss: 1.1752, Val Accuracy: 0.7366 Epoch 8409/10000, Train Loss: 1.0392, Train Accuracy: 0.8761, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8410/10000, Train Loss: 1.0579, Train Accuracy: 0.8493, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 8411/10000, Train Loss: 1.0583, Train Accuracy: 0.8482, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 8412/10000, Train Loss: 1.0472, Train Accuracy: 0.8638, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 8413/10000, Train Loss: 1.0602, Train Accuracy: 0.8471, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8414/10000, Train Loss: 1.0541, Train Accuracy: 0.8605, Val Loss: 1.1752, Val Accuracy: 0.7366 Epoch 8415/10000, Train Loss: 1.0435, Train Accuracy: 0.8694, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 8416/10000, Train Loss: 1.0509, Train Accuracy: 0.8516, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 8417/10000, Train Loss: 1.0501, Train Accuracy: 0.8650, Val Loss: 1.1750, Val Accuracy: 0.7411 Epoch 8418/10000, Train Loss: 1.0496, Train Accuracy: 0.8672, Val Loss: 1.1750, Val Accuracy: 0.7411 Epoch 8419/10000, Train Loss: 1.0401, Train Accuracy: 0.8717, Val Loss: 1.1749, Val Accuracy: 0.7411 Epoch 8420/10000, Train Loss: 1.0573, Train Accuracy: 0.8549, Val Loss: 1.1748, Val Accuracy: 0.7411 Epoch 8421/10000, Train Loss: 1.0534, Train Accuracy: 0.8571, Val Loss: 1.1750, Val Accuracy: 0.7455 Epoch 8422/10000, Train Loss: 1.0606, Train Accuracy: 0.8482, Val Loss: 1.1752, Val Accuracy: 0.7411 Epoch 8423/10000, Train Loss: 1.0359, Train Accuracy: 0.8772, Val Loss: 1.1753, Val Accuracy: 0.7411 Epoch 8424/10000, Train Loss: 1.0441, Train Accuracy: 0.8739, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 8425/10000, Train Loss: 1.0504, Train Accuracy: 0.8627, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 8426/10000, Train Loss: 1.0452, Train Accuracy: 0.8694, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 8427/10000, Train Loss: 1.0563, Train Accuracy: 0.8571, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 8428/10000, Train Loss: 1.0455, Train Accuracy: 0.8672, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 8429/10000, Train Loss: 1.0634, Train Accuracy: 0.8482, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8430/10000, Train Loss: 1.0624, Train Accuracy: 0.8482, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8431/10000, Train Loss: 1.0417, Train Accuracy: 0.8772, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8432/10000, Train Loss: 1.0540, Train Accuracy: 0.8594, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8433/10000, Train Loss: 1.0467, Train Accuracy: 0.8650, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8434/10000, Train Loss: 1.0509, Train Accuracy: 0.8594, Val Loss: 1.1752, Val Accuracy: 0.7411 Epoch 8435/10000, Train Loss: 1.0573, Train Accuracy: 0.8538, Val Loss: 1.1751, Val Accuracy: 0.7411 Epoch 8436/10000, Train Loss: 1.0510, Train Accuracy: 0.8672, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 8437/10000, Train Loss: 1.0504, Train Accuracy: 0.8638, Val Loss: 1.1752, Val Accuracy: 0.7411 Epoch 8438/10000, Train Loss: 1.0471, Train Accuracy: 0.8672, Val Loss: 1.1751, Val Accuracy: 0.7411 Epoch 8439/10000, Train Loss: 1.0553, Train Accuracy: 0.8616, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 8440/10000, Train Loss: 1.0452, Train Accuracy: 0.8650, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 8441/10000, Train Loss: 1.0532, Train Accuracy: 0.8504, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 8442/10000, Train Loss: 1.0390, Train Accuracy: 0.8783, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8443/10000, Train Loss: 1.0543, Train Accuracy: 0.8571, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8444/10000, Train Loss: 1.0561, Train Accuracy: 0.8471, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8445/10000, Train Loss: 1.0535, Train Accuracy: 0.8549, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8446/10000, Train Loss: 1.0536, Train Accuracy: 0.8583, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8447/10000, Train Loss: 1.0466, Train Accuracy: 0.8638, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8448/10000, Train Loss: 1.0593, Train Accuracy: 0.8538, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8449/10000, Train Loss: 1.0520, Train Accuracy: 0.8627, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8450/10000, Train Loss: 1.0631, Train Accuracy: 0.8493, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8451/10000, Train Loss: 1.0574, Train Accuracy: 0.8549, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8452/10000, Train Loss: 1.0405, Train Accuracy: 0.8739, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8453/10000, Train Loss: 1.0446, Train Accuracy: 0.8694, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8454/10000, Train Loss: 1.0376, Train Accuracy: 0.8806, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8455/10000, Train Loss: 1.0524, Train Accuracy: 0.8616, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8456/10000, Train Loss: 1.0412, Train Accuracy: 0.8717, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8457/10000, Train Loss: 1.0497, Train Accuracy: 0.8650, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8458/10000, Train Loss: 1.0538, Train Accuracy: 0.8594, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8459/10000, Train Loss: 1.0483, Train Accuracy: 0.8638, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8460/10000, Train Loss: 1.0498, Train Accuracy: 0.8594, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8461/10000, Train Loss: 1.0438, Train Accuracy: 0.8694, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8462/10000, Train Loss: 1.0538, Train Accuracy: 0.8549, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8463/10000, Train Loss: 1.0588, Train Accuracy: 0.8438, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8464/10000, Train Loss: 1.0539, Train Accuracy: 0.8616, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8465/10000, Train Loss: 1.0463, Train Accuracy: 0.8638, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8466/10000, Train Loss: 1.0579, Train Accuracy: 0.8527, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8467/10000, Train Loss: 1.0567, Train Accuracy: 0.8516, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8468/10000, Train Loss: 1.0557, Train Accuracy: 0.8538, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8469/10000, Train Loss: 1.0609, Train Accuracy: 0.8504, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8470/10000, Train Loss: 1.0444, Train Accuracy: 0.8694, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8471/10000, Train Loss: 1.0531, Train Accuracy: 0.8594, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8472/10000, Train Loss: 1.0591, Train Accuracy: 0.8504, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8473/10000, Train Loss: 1.0560, Train Accuracy: 0.8549, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8474/10000, Train Loss: 1.0477, Train Accuracy: 0.8650, Val Loss: 1.1769, Val Accuracy: 0.7411 Epoch 8475/10000, Train Loss: 1.0480, Train Accuracy: 0.8605, Val Loss: 1.1773, Val Accuracy: 0.7366 Epoch 8476/10000, Train Loss: 1.0611, Train Accuracy: 0.8426, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8477/10000, Train Loss: 1.0428, Train Accuracy: 0.8661, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8478/10000, Train Loss: 1.0434, Train Accuracy: 0.8616, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8479/10000, Train Loss: 1.0638, Train Accuracy: 0.8449, Val Loss: 1.1774, Val Accuracy: 0.7366 Epoch 8480/10000, Train Loss: 1.0463, Train Accuracy: 0.8616, Val Loss: 1.1772, Val Accuracy: 0.7366 Epoch 8481/10000, Train Loss: 1.0599, Train Accuracy: 0.8549, Val Loss: 1.1771, Val Accuracy: 0.7366 Epoch 8482/10000, Train Loss: 1.0503, Train Accuracy: 0.8594, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8483/10000, Train Loss: 1.0438, Train Accuracy: 0.8683, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8484/10000, Train Loss: 1.0570, Train Accuracy: 0.8594, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8485/10000, Train Loss: 1.0522, Train Accuracy: 0.8605, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8486/10000, Train Loss: 1.0613, Train Accuracy: 0.8471, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8487/10000, Train Loss: 1.0432, Train Accuracy: 0.8683, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8488/10000, Train Loss: 1.0510, Train Accuracy: 0.8538, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8489/10000, Train Loss: 1.0503, Train Accuracy: 0.8616, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8490/10000, Train Loss: 1.0609, Train Accuracy: 0.8504, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8491/10000, Train Loss: 1.0542, Train Accuracy: 0.8583, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8492/10000, Train Loss: 1.0642, Train Accuracy: 0.8560, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8493/10000, Train Loss: 1.0525, Train Accuracy: 0.8661, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8494/10000, Train Loss: 1.0580, Train Accuracy: 0.8605, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8495/10000, Train Loss: 1.0487, Train Accuracy: 0.8650, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8496/10000, Train Loss: 1.0517, Train Accuracy: 0.8616, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8497/10000, Train Loss: 1.0478, Train Accuracy: 0.8683, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8498/10000, Train Loss: 1.0465, Train Accuracy: 0.8627, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8499/10000, Train Loss: 1.0587, Train Accuracy: 0.8482, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8500/10000, Train Loss: 1.0518, Train Accuracy: 0.8560, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8501/10000, Train Loss: 1.0633, Train Accuracy: 0.8438, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8502/10000, Train Loss: 1.0495, Train Accuracy: 0.8661, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8503/10000, Train Loss: 1.0506, Train Accuracy: 0.8516, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8504/10000, Train Loss: 1.0438, Train Accuracy: 0.8683, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8505/10000, Train Loss: 1.0547, Train Accuracy: 0.8583, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8506/10000, Train Loss: 1.0472, Train Accuracy: 0.8627, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8507/10000, Train Loss: 1.0541, Train Accuracy: 0.8627, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8508/10000, Train Loss: 1.0541, Train Accuracy: 0.8516, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8509/10000, Train Loss: 1.0486, Train Accuracy: 0.8705, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8510/10000, Train Loss: 1.0615, Train Accuracy: 0.8504, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8511/10000, Train Loss: 1.0557, Train Accuracy: 0.8504, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8512/10000, Train Loss: 1.0421, Train Accuracy: 0.8705, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8513/10000, Train Loss: 1.0446, Train Accuracy: 0.8694, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8514/10000, Train Loss: 1.0544, Train Accuracy: 0.8538, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8515/10000, Train Loss: 1.0493, Train Accuracy: 0.8694, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8516/10000, Train Loss: 1.0503, Train Accuracy: 0.8650, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8517/10000, Train Loss: 1.0511, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8518/10000, Train Loss: 1.0483, Train Accuracy: 0.8638, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8519/10000, Train Loss: 1.0538, Train Accuracy: 0.8560, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8520/10000, Train Loss: 1.0444, Train Accuracy: 0.8672, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8521/10000, Train Loss: 1.0487, Train Accuracy: 0.8549, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8522/10000, Train Loss: 1.0537, Train Accuracy: 0.8538, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8523/10000, Train Loss: 1.0507, Train Accuracy: 0.8661, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8524/10000, Train Loss: 1.0538, Train Accuracy: 0.8594, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8525/10000, Train Loss: 1.0279, Train Accuracy: 0.8850, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8526/10000, Train Loss: 1.0422, Train Accuracy: 0.8728, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8527/10000, Train Loss: 1.0554, Train Accuracy: 0.8616, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8528/10000, Train Loss: 1.0485, Train Accuracy: 0.8705, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8529/10000, Train Loss: 1.0350, Train Accuracy: 0.8772, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8530/10000, Train Loss: 1.0489, Train Accuracy: 0.8650, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8531/10000, Train Loss: 1.0534, Train Accuracy: 0.8661, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8532/10000, Train Loss: 1.0512, Train Accuracy: 0.8650, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8533/10000, Train Loss: 1.0469, Train Accuracy: 0.8683, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8534/10000, Train Loss: 1.0534, Train Accuracy: 0.8571, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8535/10000, Train Loss: 1.0370, Train Accuracy: 0.8772, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8536/10000, Train Loss: 1.0420, Train Accuracy: 0.8672, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8537/10000, Train Loss: 1.0493, Train Accuracy: 0.8672, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8538/10000, Train Loss: 1.0659, Train Accuracy: 0.8493, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8539/10000, Train Loss: 1.0498, Train Accuracy: 0.8571, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8540/10000, Train Loss: 1.0460, Train Accuracy: 0.8672, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8541/10000, Train Loss: 1.0519, Train Accuracy: 0.8638, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8542/10000, Train Loss: 1.0571, Train Accuracy: 0.8605, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8543/10000, Train Loss: 1.0595, Train Accuracy: 0.8482, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8544/10000, Train Loss: 1.0484, Train Accuracy: 0.8650, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8545/10000, Train Loss: 1.0477, Train Accuracy: 0.8627, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8546/10000, Train Loss: 1.0545, Train Accuracy: 0.8571, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8547/10000, Train Loss: 1.0473, Train Accuracy: 0.8616, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8548/10000, Train Loss: 1.0378, Train Accuracy: 0.8761, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8549/10000, Train Loss: 1.0585, Train Accuracy: 0.8516, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8550/10000, Train Loss: 1.0532, Train Accuracy: 0.8650, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8551/10000, Train Loss: 1.0609, Train Accuracy: 0.8426, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8552/10000, Train Loss: 1.0694, Train Accuracy: 0.8348, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8553/10000, Train Loss: 1.0420, Train Accuracy: 0.8761, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8554/10000, Train Loss: 1.0499, Train Accuracy: 0.8594, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8555/10000, Train Loss: 1.0465, Train Accuracy: 0.8616, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8556/10000, Train Loss: 1.0423, Train Accuracy: 0.8761, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8557/10000, Train Loss: 1.0494, Train Accuracy: 0.8616, Val Loss: 1.1774, Val Accuracy: 0.7321 Epoch 8558/10000, Train Loss: 1.0614, Train Accuracy: 0.8516, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8559/10000, Train Loss: 1.0512, Train Accuracy: 0.8638, Val Loss: 1.1776, Val Accuracy: 0.7321 Epoch 8560/10000, Train Loss: 1.0426, Train Accuracy: 0.8739, Val Loss: 1.1777, Val Accuracy: 0.7277 Epoch 8561/10000, Train Loss: 1.0572, Train Accuracy: 0.8549, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8562/10000, Train Loss: 1.0486, Train Accuracy: 0.8683, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8563/10000, Train Loss: 1.0501, Train Accuracy: 0.8605, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8564/10000, Train Loss: 1.0555, Train Accuracy: 0.8594, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8565/10000, Train Loss: 1.0540, Train Accuracy: 0.8504, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8566/10000, Train Loss: 1.0369, Train Accuracy: 0.8728, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8567/10000, Train Loss: 1.0542, Train Accuracy: 0.8560, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8568/10000, Train Loss: 1.0465, Train Accuracy: 0.8638, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8569/10000, Train Loss: 1.0532, Train Accuracy: 0.8583, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8570/10000, Train Loss: 1.0512, Train Accuracy: 0.8672, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8571/10000, Train Loss: 1.0459, Train Accuracy: 0.8672, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8572/10000, Train Loss: 1.0594, Train Accuracy: 0.8493, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8573/10000, Train Loss: 1.0497, Train Accuracy: 0.8605, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8574/10000, Train Loss: 1.0499, Train Accuracy: 0.8571, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8575/10000, Train Loss: 1.0396, Train Accuracy: 0.8761, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8576/10000, Train Loss: 1.0513, Train Accuracy: 0.8594, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8577/10000, Train Loss: 1.0460, Train Accuracy: 0.8571, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8578/10000, Train Loss: 1.0461, Train Accuracy: 0.8616, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8579/10000, Train Loss: 1.0532, Train Accuracy: 0.8583, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8580/10000, Train Loss: 1.0394, Train Accuracy: 0.8705, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8581/10000, Train Loss: 1.0447, Train Accuracy: 0.8705, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8582/10000, Train Loss: 1.0465, Train Accuracy: 0.8717, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8583/10000, Train Loss: 1.0479, Train Accuracy: 0.8605, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8584/10000, Train Loss: 1.0482, Train Accuracy: 0.8594, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8585/10000, Train Loss: 1.0501, Train Accuracy: 0.8571, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8586/10000, Train Loss: 1.0449, Train Accuracy: 0.8683, Val Loss: 1.1774, Val Accuracy: 0.7321 Epoch 8587/10000, Train Loss: 1.0499, Train Accuracy: 0.8728, Val Loss: 1.1774, Val Accuracy: 0.7321 Epoch 8588/10000, Train Loss: 1.0454, Train Accuracy: 0.8728, Val Loss: 1.1777, Val Accuracy: 0.7321 Epoch 8589/10000, Train Loss: 1.0454, Train Accuracy: 0.8672, Val Loss: 1.1780, Val Accuracy: 0.7277 Epoch 8590/10000, Train Loss: 1.0439, Train Accuracy: 0.8694, Val Loss: 1.1778, Val Accuracy: 0.7277 Epoch 8591/10000, Train Loss: 1.0486, Train Accuracy: 0.8650, Val Loss: 1.1776, Val Accuracy: 0.7277 Epoch 8592/10000, Train Loss: 1.0441, Train Accuracy: 0.8717, Val Loss: 1.1777, Val Accuracy: 0.7321 Epoch 8593/10000, Train Loss: 1.0470, Train Accuracy: 0.8627, Val Loss: 1.1776, Val Accuracy: 0.7321 Epoch 8594/10000, Train Loss: 1.0339, Train Accuracy: 0.8873, Val Loss: 1.1775, Val Accuracy: 0.7277 Epoch 8595/10000, Train Loss: 1.0531, Train Accuracy: 0.8638, Val Loss: 1.1777, Val Accuracy: 0.7277 Epoch 8596/10000, Train Loss: 1.0573, Train Accuracy: 0.8527, Val Loss: 1.1776, Val Accuracy: 0.7321 Epoch 8597/10000, Train Loss: 1.0480, Train Accuracy: 0.8638, Val Loss: 1.1777, Val Accuracy: 0.7366 Epoch 8598/10000, Train Loss: 1.0386, Train Accuracy: 0.8761, Val Loss: 1.1778, Val Accuracy: 0.7321 Epoch 8599/10000, Train Loss: 1.0619, Train Accuracy: 0.8404, Val Loss: 1.1778, Val Accuracy: 0.7321 Epoch 8600/10000, Train Loss: 1.0474, Train Accuracy: 0.8672, Val Loss: 1.1778, Val Accuracy: 0.7277 Epoch 8601/10000, Train Loss: 1.0432, Train Accuracy: 0.8705, Val Loss: 1.1778, Val Accuracy: 0.7277 Epoch 8602/10000, Train Loss: 1.0435, Train Accuracy: 0.8683, Val Loss: 1.1778, Val Accuracy: 0.7277 Epoch 8603/10000, Train Loss: 1.0475, Train Accuracy: 0.8694, Val Loss: 1.1780, Val Accuracy: 0.7232 Epoch 8604/10000, Train Loss: 1.0421, Train Accuracy: 0.8694, Val Loss: 1.1778, Val Accuracy: 0.7277 Epoch 8605/10000, Train Loss: 1.0637, Train Accuracy: 0.8382, Val Loss: 1.1779, Val Accuracy: 0.7232 Epoch 8606/10000, Train Loss: 1.0478, Train Accuracy: 0.8627, Val Loss: 1.1780, Val Accuracy: 0.7232 Epoch 8607/10000, Train Loss: 1.0424, Train Accuracy: 0.8694, Val Loss: 1.1779, Val Accuracy: 0.7277 Epoch 8608/10000, Train Loss: 1.0549, Train Accuracy: 0.8549, Val Loss: 1.1777, Val Accuracy: 0.7321 Epoch 8609/10000, Train Loss: 1.0605, Train Accuracy: 0.8449, Val Loss: 1.1778, Val Accuracy: 0.7321 Epoch 8610/10000, Train Loss: 1.0316, Train Accuracy: 0.8783, Val Loss: 1.1779, Val Accuracy: 0.7277 Epoch 8611/10000, Train Loss: 1.0483, Train Accuracy: 0.8638, Val Loss: 1.1775, Val Accuracy: 0.7321 Epoch 8612/10000, Train Loss: 1.0457, Train Accuracy: 0.8672, Val Loss: 1.1776, Val Accuracy: 0.7366 Epoch 8613/10000, Train Loss: 1.0464, Train Accuracy: 0.8694, Val Loss: 1.1775, Val Accuracy: 0.7321 Epoch 8614/10000, Train Loss: 1.0443, Train Accuracy: 0.8683, Val Loss: 1.1775, Val Accuracy: 0.7321 Epoch 8615/10000, Train Loss: 1.0538, Train Accuracy: 0.8594, Val Loss: 1.1778, Val Accuracy: 0.7277 Epoch 8616/10000, Train Loss: 1.0608, Train Accuracy: 0.8449, Val Loss: 1.1776, Val Accuracy: 0.7277 Epoch 8617/10000, Train Loss: 1.0426, Train Accuracy: 0.8705, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8618/10000, Train Loss: 1.0494, Train Accuracy: 0.8650, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8619/10000, Train Loss: 1.0474, Train Accuracy: 0.8661, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8620/10000, Train Loss: 1.0349, Train Accuracy: 0.8783, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8621/10000, Train Loss: 1.0422, Train Accuracy: 0.8705, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8622/10000, Train Loss: 1.0404, Train Accuracy: 0.8672, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8623/10000, Train Loss: 1.0423, Train Accuracy: 0.8728, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8624/10000, Train Loss: 1.0334, Train Accuracy: 0.8884, Val Loss: 1.1769, Val Accuracy: 0.7366 Epoch 8625/10000, Train Loss: 1.0562, Train Accuracy: 0.8549, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8626/10000, Train Loss: 1.0470, Train Accuracy: 0.8694, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8627/10000, Train Loss: 1.0541, Train Accuracy: 0.8504, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8628/10000, Train Loss: 1.0480, Train Accuracy: 0.8683, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8629/10000, Train Loss: 1.0489, Train Accuracy: 0.8549, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8630/10000, Train Loss: 1.0491, Train Accuracy: 0.8627, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8631/10000, Train Loss: 1.0534, Train Accuracy: 0.8605, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8632/10000, Train Loss: 1.0392, Train Accuracy: 0.8761, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8633/10000, Train Loss: 1.0516, Train Accuracy: 0.8571, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8634/10000, Train Loss: 1.0502, Train Accuracy: 0.8672, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8635/10000, Train Loss: 1.0448, Train Accuracy: 0.8650, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 8636/10000, Train Loss: 1.0409, Train Accuracy: 0.8717, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 8637/10000, Train Loss: 1.0486, Train Accuracy: 0.8583, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8638/10000, Train Loss: 1.0465, Train Accuracy: 0.8694, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8639/10000, Train Loss: 1.0590, Train Accuracy: 0.8482, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8640/10000, Train Loss: 1.0497, Train Accuracy: 0.8594, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 8641/10000, Train Loss: 1.0614, Train Accuracy: 0.8538, Val Loss: 1.1762, Val Accuracy: 0.7277 Epoch 8642/10000, Train Loss: 1.0507, Train Accuracy: 0.8583, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 8643/10000, Train Loss: 1.0456, Train Accuracy: 0.8705, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 8644/10000, Train Loss: 1.0397, Train Accuracy: 0.8739, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8645/10000, Train Loss: 1.0436, Train Accuracy: 0.8661, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 8646/10000, Train Loss: 1.0419, Train Accuracy: 0.8761, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8647/10000, Train Loss: 1.0499, Train Accuracy: 0.8571, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 8648/10000, Train Loss: 1.0567, Train Accuracy: 0.8560, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 8649/10000, Train Loss: 1.0473, Train Accuracy: 0.8672, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8650/10000, Train Loss: 1.0525, Train Accuracy: 0.8571, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 8651/10000, Train Loss: 1.0431, Train Accuracy: 0.8650, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 8652/10000, Train Loss: 1.0488, Train Accuracy: 0.8605, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8653/10000, Train Loss: 1.0564, Train Accuracy: 0.8549, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8654/10000, Train Loss: 1.0477, Train Accuracy: 0.8672, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8655/10000, Train Loss: 1.0443, Train Accuracy: 0.8661, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8656/10000, Train Loss: 1.0474, Train Accuracy: 0.8627, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 8657/10000, Train Loss: 1.0420, Train Accuracy: 0.8694, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8658/10000, Train Loss: 1.0398, Train Accuracy: 0.8761, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8659/10000, Train Loss: 1.0365, Train Accuracy: 0.8795, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 8660/10000, Train Loss: 1.0397, Train Accuracy: 0.8739, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 8661/10000, Train Loss: 1.0515, Train Accuracy: 0.8605, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8662/10000, Train Loss: 1.0331, Train Accuracy: 0.8772, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8663/10000, Train Loss: 1.0506, Train Accuracy: 0.8638, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 8664/10000, Train Loss: 1.0436, Train Accuracy: 0.8661, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8665/10000, Train Loss: 1.0428, Train Accuracy: 0.8728, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 8666/10000, Train Loss: 1.0490, Train Accuracy: 0.8616, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 8667/10000, Train Loss: 1.0463, Train Accuracy: 0.8661, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 8668/10000, Train Loss: 1.0448, Train Accuracy: 0.8672, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 8669/10000, Train Loss: 1.0507, Train Accuracy: 0.8605, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 8670/10000, Train Loss: 1.0508, Train Accuracy: 0.8616, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 8671/10000, Train Loss: 1.0330, Train Accuracy: 0.8761, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 8672/10000, Train Loss: 1.0505, Train Accuracy: 0.8616, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8673/10000, Train Loss: 1.0468, Train Accuracy: 0.8650, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8674/10000, Train Loss: 1.0361, Train Accuracy: 0.8806, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8675/10000, Train Loss: 1.0482, Train Accuracy: 0.8650, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 8676/10000, Train Loss: 1.0610, Train Accuracy: 0.8504, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 8677/10000, Train Loss: 1.0435, Train Accuracy: 0.8672, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8678/10000, Train Loss: 1.0453, Train Accuracy: 0.8627, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 8679/10000, Train Loss: 1.0395, Train Accuracy: 0.8772, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 8680/10000, Train Loss: 1.0425, Train Accuracy: 0.8739, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 8681/10000, Train Loss: 1.0465, Train Accuracy: 0.8638, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8682/10000, Train Loss: 1.0470, Train Accuracy: 0.8627, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8683/10000, Train Loss: 1.0532, Train Accuracy: 0.8493, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8684/10000, Train Loss: 1.0478, Train Accuracy: 0.8583, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8685/10000, Train Loss: 1.0516, Train Accuracy: 0.8594, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8686/10000, Train Loss: 1.0456, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8687/10000, Train Loss: 1.0378, Train Accuracy: 0.8761, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8688/10000, Train Loss: 1.0397, Train Accuracy: 0.8717, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8689/10000, Train Loss: 1.0603, Train Accuracy: 0.8493, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8690/10000, Train Loss: 1.0602, Train Accuracy: 0.8538, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8691/10000, Train Loss: 1.0299, Train Accuracy: 0.8873, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8692/10000, Train Loss: 1.0477, Train Accuracy: 0.8616, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8693/10000, Train Loss: 1.0542, Train Accuracy: 0.8616, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8694/10000, Train Loss: 1.0495, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8695/10000, Train Loss: 1.0517, Train Accuracy: 0.8538, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8696/10000, Train Loss: 1.0465, Train Accuracy: 0.8661, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8697/10000, Train Loss: 1.0525, Train Accuracy: 0.8583, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8698/10000, Train Loss: 1.0498, Train Accuracy: 0.8650, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8699/10000, Train Loss: 1.0410, Train Accuracy: 0.8728, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8700/10000, Train Loss: 1.0521, Train Accuracy: 0.8616, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8701/10000, Train Loss: 1.0485, Train Accuracy: 0.8672, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8702/10000, Train Loss: 1.0478, Train Accuracy: 0.8627, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8703/10000, Train Loss: 1.0564, Train Accuracy: 0.8460, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8704/10000, Train Loss: 1.0436, Train Accuracy: 0.8761, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8705/10000, Train Loss: 1.0525, Train Accuracy: 0.8616, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8706/10000, Train Loss: 1.0548, Train Accuracy: 0.8560, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8707/10000, Train Loss: 1.0401, Train Accuracy: 0.8717, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8708/10000, Train Loss: 1.0428, Train Accuracy: 0.8672, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8709/10000, Train Loss: 1.0399, Train Accuracy: 0.8705, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 8710/10000, Train Loss: 1.0492, Train Accuracy: 0.8605, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8711/10000, Train Loss: 1.0355, Train Accuracy: 0.8761, Val Loss: 1.1761, Val Accuracy: 0.7321 Epoch 8712/10000, Train Loss: 1.0479, Train Accuracy: 0.8616, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 8713/10000, Train Loss: 1.0367, Train Accuracy: 0.8761, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8714/10000, Train Loss: 1.0575, Train Accuracy: 0.8538, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8715/10000, Train Loss: 1.0495, Train Accuracy: 0.8616, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8716/10000, Train Loss: 1.0494, Train Accuracy: 0.8672, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8717/10000, Train Loss: 1.0485, Train Accuracy: 0.8605, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8718/10000, Train Loss: 1.0547, Train Accuracy: 0.8571, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8719/10000, Train Loss: 1.0397, Train Accuracy: 0.8705, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8720/10000, Train Loss: 1.0434, Train Accuracy: 0.8672, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8721/10000, Train Loss: 1.0510, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8722/10000, Train Loss: 1.0433, Train Accuracy: 0.8672, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8723/10000, Train Loss: 1.0455, Train Accuracy: 0.8705, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8724/10000, Train Loss: 1.0455, Train Accuracy: 0.8638, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8725/10000, Train Loss: 1.0507, Train Accuracy: 0.8605, Val Loss: 1.1775, Val Accuracy: 0.7321 Epoch 8726/10000, Train Loss: 1.0455, Train Accuracy: 0.8683, Val Loss: 1.1774, Val Accuracy: 0.7321 Epoch 8727/10000, Train Loss: 1.0482, Train Accuracy: 0.8627, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8728/10000, Train Loss: 1.0472, Train Accuracy: 0.8650, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8729/10000, Train Loss: 1.0427, Train Accuracy: 0.8750, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8730/10000, Train Loss: 1.0422, Train Accuracy: 0.8717, Val Loss: 1.1774, Val Accuracy: 0.7321 Epoch 8731/10000, Train Loss: 1.0384, Train Accuracy: 0.8705, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8732/10000, Train Loss: 1.0345, Train Accuracy: 0.8783, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8733/10000, Train Loss: 1.0617, Train Accuracy: 0.8415, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8734/10000, Train Loss: 1.0471, Train Accuracy: 0.8694, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8735/10000, Train Loss: 1.0413, Train Accuracy: 0.8705, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8736/10000, Train Loss: 1.0454, Train Accuracy: 0.8661, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8737/10000, Train Loss: 1.0379, Train Accuracy: 0.8783, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8738/10000, Train Loss: 1.0425, Train Accuracy: 0.8717, Val Loss: 1.1776, Val Accuracy: 0.7321 Epoch 8739/10000, Train Loss: 1.0433, Train Accuracy: 0.8627, Val Loss: 1.1775, Val Accuracy: 0.7321 Epoch 8740/10000, Train Loss: 1.0392, Train Accuracy: 0.8739, Val Loss: 1.1775, Val Accuracy: 0.7321 Epoch 8741/10000, Train Loss: 1.0414, Train Accuracy: 0.8705, Val Loss: 1.1773, Val Accuracy: 0.7321 Epoch 8742/10000, Train Loss: 1.0425, Train Accuracy: 0.8750, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8743/10000, Train Loss: 1.0492, Train Accuracy: 0.8605, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8744/10000, Train Loss: 1.0372, Train Accuracy: 0.8772, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8745/10000, Train Loss: 1.0397, Train Accuracy: 0.8728, Val Loss: 1.1772, Val Accuracy: 0.7321 Epoch 8746/10000, Train Loss: 1.0430, Train Accuracy: 0.8705, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8747/10000, Train Loss: 1.0363, Train Accuracy: 0.8750, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8748/10000, Train Loss: 1.0474, Train Accuracy: 0.8616, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8749/10000, Train Loss: 1.0357, Train Accuracy: 0.8761, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8750/10000, Train Loss: 1.0417, Train Accuracy: 0.8750, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8751/10000, Train Loss: 1.0437, Train Accuracy: 0.8728, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8752/10000, Train Loss: 1.0345, Train Accuracy: 0.8783, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8753/10000, Train Loss: 1.0600, Train Accuracy: 0.8460, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8754/10000, Train Loss: 1.0451, Train Accuracy: 0.8705, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8755/10000, Train Loss: 1.0488, Train Accuracy: 0.8571, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8756/10000, Train Loss: 1.0518, Train Accuracy: 0.8549, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8757/10000, Train Loss: 1.0363, Train Accuracy: 0.8761, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8758/10000, Train Loss: 1.0414, Train Accuracy: 0.8717, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8759/10000, Train Loss: 1.0388, Train Accuracy: 0.8694, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8760/10000, Train Loss: 1.0458, Train Accuracy: 0.8683, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8761/10000, Train Loss: 1.0526, Train Accuracy: 0.8616, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8762/10000, Train Loss: 1.0441, Train Accuracy: 0.8650, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8763/10000, Train Loss: 1.0336, Train Accuracy: 0.8806, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8764/10000, Train Loss: 1.0442, Train Accuracy: 0.8661, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8765/10000, Train Loss: 1.0640, Train Accuracy: 0.8504, Val Loss: 1.1770, Val Accuracy: 0.7366 Epoch 8766/10000, Train Loss: 1.0472, Train Accuracy: 0.8650, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8767/10000, Train Loss: 1.0514, Train Accuracy: 0.8605, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8768/10000, Train Loss: 1.0506, Train Accuracy: 0.8672, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8769/10000, Train Loss: 1.0453, Train Accuracy: 0.8683, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8770/10000, Train Loss: 1.0366, Train Accuracy: 0.8705, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8771/10000, Train Loss: 1.0368, Train Accuracy: 0.8728, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8772/10000, Train Loss: 1.0402, Train Accuracy: 0.8761, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8773/10000, Train Loss: 1.0501, Train Accuracy: 0.8672, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8774/10000, Train Loss: 1.0352, Train Accuracy: 0.8828, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8775/10000, Train Loss: 1.0445, Train Accuracy: 0.8638, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8776/10000, Train Loss: 1.0498, Train Accuracy: 0.8638, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8777/10000, Train Loss: 1.0451, Train Accuracy: 0.8638, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8778/10000, Train Loss: 1.0590, Train Accuracy: 0.8527, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8779/10000, Train Loss: 1.0413, Train Accuracy: 0.8761, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8780/10000, Train Loss: 1.0439, Train Accuracy: 0.8717, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8781/10000, Train Loss: 1.0425, Train Accuracy: 0.8739, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8782/10000, Train Loss: 1.0429, Train Accuracy: 0.8683, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8783/10000, Train Loss: 1.0325, Train Accuracy: 0.8761, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8784/10000, Train Loss: 1.0503, Train Accuracy: 0.8605, Val Loss: 1.1767, Val Accuracy: 0.7366 Epoch 8785/10000, Train Loss: 1.0347, Train Accuracy: 0.8761, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8786/10000, Train Loss: 1.0386, Train Accuracy: 0.8705, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8787/10000, Train Loss: 1.0481, Train Accuracy: 0.8627, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8788/10000, Train Loss: 1.0296, Train Accuracy: 0.8828, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8789/10000, Train Loss: 1.0519, Train Accuracy: 0.8605, Val Loss: 1.1766, Val Accuracy: 0.7366 Epoch 8790/10000, Train Loss: 1.0418, Train Accuracy: 0.8638, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8791/10000, Train Loss: 1.0490, Train Accuracy: 0.8583, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8792/10000, Train Loss: 1.0375, Train Accuracy: 0.8783, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8793/10000, Train Loss: 1.0443, Train Accuracy: 0.8650, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8794/10000, Train Loss: 1.0511, Train Accuracy: 0.8616, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8795/10000, Train Loss: 1.0383, Train Accuracy: 0.8761, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8796/10000, Train Loss: 1.0498, Train Accuracy: 0.8605, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8797/10000, Train Loss: 1.0485, Train Accuracy: 0.8650, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8798/10000, Train Loss: 1.0515, Train Accuracy: 0.8627, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8799/10000, Train Loss: 1.0544, Train Accuracy: 0.8560, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8800/10000, Train Loss: 1.0489, Train Accuracy: 0.8650, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8801/10000, Train Loss: 1.0530, Train Accuracy: 0.8560, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8802/10000, Train Loss: 1.0380, Train Accuracy: 0.8739, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8803/10000, Train Loss: 1.0396, Train Accuracy: 0.8672, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8804/10000, Train Loss: 1.0461, Train Accuracy: 0.8672, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8805/10000, Train Loss: 1.0503, Train Accuracy: 0.8638, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8806/10000, Train Loss: 1.0382, Train Accuracy: 0.8806, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8807/10000, Train Loss: 1.0420, Train Accuracy: 0.8772, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8808/10000, Train Loss: 1.0497, Train Accuracy: 0.8594, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8809/10000, Train Loss: 1.0400, Train Accuracy: 0.8739, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8810/10000, Train Loss: 1.0486, Train Accuracy: 0.8717, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8811/10000, Train Loss: 1.0455, Train Accuracy: 0.8672, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8812/10000, Train Loss: 1.0298, Train Accuracy: 0.8850, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8813/10000, Train Loss: 1.0454, Train Accuracy: 0.8694, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8814/10000, Train Loss: 1.0446, Train Accuracy: 0.8683, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8815/10000, Train Loss: 1.0414, Train Accuracy: 0.8683, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8816/10000, Train Loss: 1.0372, Train Accuracy: 0.8806, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8817/10000, Train Loss: 1.0464, Train Accuracy: 0.8661, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8818/10000, Train Loss: 1.0457, Train Accuracy: 0.8672, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8819/10000, Train Loss: 1.0385, Train Accuracy: 0.8761, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8820/10000, Train Loss: 1.0476, Train Accuracy: 0.8672, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8821/10000, Train Loss: 1.0500, Train Accuracy: 0.8638, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8822/10000, Train Loss: 1.0417, Train Accuracy: 0.8694, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8823/10000, Train Loss: 1.0444, Train Accuracy: 0.8638, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8824/10000, Train Loss: 1.0478, Train Accuracy: 0.8538, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8825/10000, Train Loss: 1.0496, Train Accuracy: 0.8571, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8826/10000, Train Loss: 1.0449, Train Accuracy: 0.8605, Val Loss: 1.1762, Val Accuracy: 0.7366 Epoch 8827/10000, Train Loss: 1.0498, Train Accuracy: 0.8627, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8828/10000, Train Loss: 1.0496, Train Accuracy: 0.8594, Val Loss: 1.1768, Val Accuracy: 0.7366 Epoch 8829/10000, Train Loss: 1.0526, Train Accuracy: 0.8638, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8830/10000, Train Loss: 1.0448, Train Accuracy: 0.8672, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8831/10000, Train Loss: 1.0364, Train Accuracy: 0.8717, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8832/10000, Train Loss: 1.0425, Train Accuracy: 0.8672, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8833/10000, Train Loss: 1.0407, Train Accuracy: 0.8750, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8834/10000, Train Loss: 1.0459, Train Accuracy: 0.8638, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8835/10000, Train Loss: 1.0387, Train Accuracy: 0.8672, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8836/10000, Train Loss: 1.0383, Train Accuracy: 0.8761, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8837/10000, Train Loss: 1.0460, Train Accuracy: 0.8627, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8838/10000, Train Loss: 1.0560, Train Accuracy: 0.8527, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8839/10000, Train Loss: 1.0457, Train Accuracy: 0.8661, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8840/10000, Train Loss: 1.0343, Train Accuracy: 0.8828, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8841/10000, Train Loss: 1.0486, Train Accuracy: 0.8661, Val Loss: 1.1769, Val Accuracy: 0.7321 Epoch 8842/10000, Train Loss: 1.0397, Train Accuracy: 0.8705, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8843/10000, Train Loss: 1.0456, Train Accuracy: 0.8627, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8844/10000, Train Loss: 1.0438, Train Accuracy: 0.8638, Val Loss: 1.1771, Val Accuracy: 0.7277 Epoch 8845/10000, Train Loss: 1.0286, Train Accuracy: 0.8817, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8846/10000, Train Loss: 1.0442, Train Accuracy: 0.8627, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8847/10000, Train Loss: 1.0376, Train Accuracy: 0.8772, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8848/10000, Train Loss: 1.0492, Train Accuracy: 0.8583, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8849/10000, Train Loss: 1.0508, Train Accuracy: 0.8594, Val Loss: 1.1771, Val Accuracy: 0.7277 Epoch 8850/10000, Train Loss: 1.0522, Train Accuracy: 0.8583, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 8851/10000, Train Loss: 1.0480, Train Accuracy: 0.8594, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 8852/10000, Train Loss: 1.0420, Train Accuracy: 0.8672, Val Loss: 1.1770, Val Accuracy: 0.7277 Epoch 8853/10000, Train Loss: 1.0471, Train Accuracy: 0.8672, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 8854/10000, Train Loss: 1.0542, Train Accuracy: 0.8527, Val Loss: 1.1771, Val Accuracy: 0.7277 Epoch 8855/10000, Train Loss: 1.0422, Train Accuracy: 0.8661, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8856/10000, Train Loss: 1.0483, Train Accuracy: 0.8650, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8857/10000, Train Loss: 1.0462, Train Accuracy: 0.8605, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8858/10000, Train Loss: 1.0435, Train Accuracy: 0.8650, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8859/10000, Train Loss: 1.0464, Train Accuracy: 0.8683, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8860/10000, Train Loss: 1.0369, Train Accuracy: 0.8750, Val Loss: 1.1777, Val Accuracy: 0.7277 Epoch 8861/10000, Train Loss: 1.0397, Train Accuracy: 0.8728, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8862/10000, Train Loss: 1.0343, Train Accuracy: 0.8772, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8863/10000, Train Loss: 1.0445, Train Accuracy: 0.8694, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8864/10000, Train Loss: 1.0500, Train Accuracy: 0.8616, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8865/10000, Train Loss: 1.0505, Train Accuracy: 0.8527, Val Loss: 1.1775, Val Accuracy: 0.7277 Epoch 8866/10000, Train Loss: 1.0315, Train Accuracy: 0.8817, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8867/10000, Train Loss: 1.0500, Train Accuracy: 0.8605, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8868/10000, Train Loss: 1.0348, Train Accuracy: 0.8739, Val Loss: 1.1775, Val Accuracy: 0.7277 Epoch 8869/10000, Train Loss: 1.0395, Train Accuracy: 0.8705, Val Loss: 1.1775, Val Accuracy: 0.7277 Epoch 8870/10000, Train Loss: 1.0436, Train Accuracy: 0.8683, Val Loss: 1.1777, Val Accuracy: 0.7277 Epoch 8871/10000, Train Loss: 1.0437, Train Accuracy: 0.8694, Val Loss: 1.1776, Val Accuracy: 0.7277 Epoch 8872/10000, Train Loss: 1.0440, Train Accuracy: 0.8683, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8873/10000, Train Loss: 1.0396, Train Accuracy: 0.8694, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8874/10000, Train Loss: 1.0502, Train Accuracy: 0.8594, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8875/10000, Train Loss: 1.0445, Train Accuracy: 0.8638, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8876/10000, Train Loss: 1.0503, Train Accuracy: 0.8594, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8877/10000, Train Loss: 1.0365, Train Accuracy: 0.8739, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8878/10000, Train Loss: 1.0377, Train Accuracy: 0.8795, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8879/10000, Train Loss: 1.0354, Train Accuracy: 0.8795, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8880/10000, Train Loss: 1.0414, Train Accuracy: 0.8739, Val Loss: 1.1771, Val Accuracy: 0.7277 Epoch 8881/10000, Train Loss: 1.0418, Train Accuracy: 0.8717, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 8882/10000, Train Loss: 1.0582, Train Accuracy: 0.8571, Val Loss: 1.1770, Val Accuracy: 0.7277 Epoch 8883/10000, Train Loss: 1.0428, Train Accuracy: 0.8739, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8884/10000, Train Loss: 1.0423, Train Accuracy: 0.8717, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8885/10000, Train Loss: 1.0509, Train Accuracy: 0.8583, Val Loss: 1.1767, Val Accuracy: 0.7321 Epoch 8886/10000, Train Loss: 1.0474, Train Accuracy: 0.8650, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 8887/10000, Train Loss: 1.0256, Train Accuracy: 0.8817, Val Loss: 1.1768, Val Accuracy: 0.7277 Epoch 8888/10000, Train Loss: 1.0386, Train Accuracy: 0.8694, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8889/10000, Train Loss: 1.0410, Train Accuracy: 0.8683, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8890/10000, Train Loss: 1.0396, Train Accuracy: 0.8739, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8891/10000, Train Loss: 1.0445, Train Accuracy: 0.8638, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8892/10000, Train Loss: 1.0547, Train Accuracy: 0.8616, Val Loss: 1.1771, Val Accuracy: 0.7321 Epoch 8893/10000, Train Loss: 1.0357, Train Accuracy: 0.8806, Val Loss: 1.1770, Val Accuracy: 0.7321 Epoch 8894/10000, Train Loss: 1.0435, Train Accuracy: 0.8638, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8895/10000, Train Loss: 1.0409, Train Accuracy: 0.8694, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8896/10000, Train Loss: 1.0497, Train Accuracy: 0.8616, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8897/10000, Train Loss: 1.0550, Train Accuracy: 0.8571, Val Loss: 1.1775, Val Accuracy: 0.7277 Epoch 8898/10000, Train Loss: 1.0430, Train Accuracy: 0.8705, Val Loss: 1.1773, Val Accuracy: 0.7277 Epoch 8899/10000, Train Loss: 1.0429, Train Accuracy: 0.8750, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 8900/10000, Train Loss: 1.0515, Train Accuracy: 0.8683, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 8901/10000, Train Loss: 1.0388, Train Accuracy: 0.8717, Val Loss: 1.1770, Val Accuracy: 0.7277 Epoch 8902/10000, Train Loss: 1.0421, Train Accuracy: 0.8705, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 8903/10000, Train Loss: 1.0531, Train Accuracy: 0.8527, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 8904/10000, Train Loss: 1.0355, Train Accuracy: 0.8806, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 8905/10000, Train Loss: 1.0242, Train Accuracy: 0.8917, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8906/10000, Train Loss: 1.0395, Train Accuracy: 0.8772, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 8907/10000, Train Loss: 1.0419, Train Accuracy: 0.8728, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8908/10000, Train Loss: 1.0407, Train Accuracy: 0.8739, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8909/10000, Train Loss: 1.0376, Train Accuracy: 0.8739, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 8910/10000, Train Loss: 1.0325, Train Accuracy: 0.8817, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 8911/10000, Train Loss: 1.0453, Train Accuracy: 0.8616, Val Loss: 1.1764, Val Accuracy: 0.7277 Epoch 8912/10000, Train Loss: 1.0419, Train Accuracy: 0.8672, Val Loss: 1.1766, Val Accuracy: 0.7277 Epoch 8913/10000, Train Loss: 1.0401, Train Accuracy: 0.8683, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 8914/10000, Train Loss: 1.0541, Train Accuracy: 0.8605, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 8915/10000, Train Loss: 1.0436, Train Accuracy: 0.8661, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8916/10000, Train Loss: 1.0368, Train Accuracy: 0.8739, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 8917/10000, Train Loss: 1.0365, Train Accuracy: 0.8817, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 8918/10000, Train Loss: 1.0428, Train Accuracy: 0.8661, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 8919/10000, Train Loss: 1.0360, Train Accuracy: 0.8795, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 8920/10000, Train Loss: 1.0562, Train Accuracy: 0.8504, Val Loss: 1.1764, Val Accuracy: 0.7321 Epoch 8921/10000, Train Loss: 1.0415, Train Accuracy: 0.8672, Val Loss: 1.1765, Val Accuracy: 0.7366 Epoch 8922/10000, Train Loss: 1.0464, Train Accuracy: 0.8616, Val Loss: 1.1763, Val Accuracy: 0.7411 Epoch 8923/10000, Train Loss: 1.0477, Train Accuracy: 0.8672, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 8924/10000, Train Loss: 1.0499, Train Accuracy: 0.8605, Val Loss: 1.1765, Val Accuracy: 0.7411 Epoch 8925/10000, Train Loss: 1.0500, Train Accuracy: 0.8560, Val Loss: 1.1763, Val Accuracy: 0.7411 Epoch 8926/10000, Train Loss: 1.0344, Train Accuracy: 0.8783, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8927/10000, Train Loss: 1.0462, Train Accuracy: 0.8616, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8928/10000, Train Loss: 1.0462, Train Accuracy: 0.8650, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8929/10000, Train Loss: 1.0463, Train Accuracy: 0.8661, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 8930/10000, Train Loss: 1.0493, Train Accuracy: 0.8638, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 8931/10000, Train Loss: 1.0324, Train Accuracy: 0.8806, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 8932/10000, Train Loss: 1.0294, Train Accuracy: 0.8862, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 8933/10000, Train Loss: 1.0488, Train Accuracy: 0.8638, Val Loss: 1.1761, Val Accuracy: 0.7321 Epoch 8934/10000, Train Loss: 1.0404, Train Accuracy: 0.8672, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 8935/10000, Train Loss: 1.0323, Train Accuracy: 0.8806, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 8936/10000, Train Loss: 1.0441, Train Accuracy: 0.8650, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 8937/10000, Train Loss: 1.0437, Train Accuracy: 0.8705, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 8938/10000, Train Loss: 1.0407, Train Accuracy: 0.8717, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8939/10000, Train Loss: 1.0451, Train Accuracy: 0.8739, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 8940/10000, Train Loss: 1.0480, Train Accuracy: 0.8605, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 8941/10000, Train Loss: 1.0399, Train Accuracy: 0.8717, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8942/10000, Train Loss: 1.0443, Train Accuracy: 0.8717, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8943/10000, Train Loss: 1.0389, Train Accuracy: 0.8705, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8944/10000, Train Loss: 1.0340, Train Accuracy: 0.8862, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8945/10000, Train Loss: 1.0627, Train Accuracy: 0.8471, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8946/10000, Train Loss: 1.0421, Train Accuracy: 0.8683, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8947/10000, Train Loss: 1.0384, Train Accuracy: 0.8717, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8948/10000, Train Loss: 1.0523, Train Accuracy: 0.8605, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8949/10000, Train Loss: 1.0468, Train Accuracy: 0.8650, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8950/10000, Train Loss: 1.0300, Train Accuracy: 0.8839, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8951/10000, Train Loss: 1.0438, Train Accuracy: 0.8717, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8952/10000, Train Loss: 1.0324, Train Accuracy: 0.8806, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8953/10000, Train Loss: 1.0302, Train Accuracy: 0.8873, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 8954/10000, Train Loss: 1.0405, Train Accuracy: 0.8761, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 8955/10000, Train Loss: 1.0405, Train Accuracy: 0.8705, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8956/10000, Train Loss: 1.0357, Train Accuracy: 0.8772, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8957/10000, Train Loss: 1.0471, Train Accuracy: 0.8672, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 8958/10000, Train Loss: 1.0300, Train Accuracy: 0.8884, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 8959/10000, Train Loss: 1.0353, Train Accuracy: 0.8795, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 8960/10000, Train Loss: 1.0363, Train Accuracy: 0.8750, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8961/10000, Train Loss: 1.0347, Train Accuracy: 0.8783, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8962/10000, Train Loss: 1.0443, Train Accuracy: 0.8672, Val Loss: 1.1752, Val Accuracy: 0.7366 Epoch 8963/10000, Train Loss: 1.0441, Train Accuracy: 0.8638, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8964/10000, Train Loss: 1.0459, Train Accuracy: 0.8627, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8965/10000, Train Loss: 1.0374, Train Accuracy: 0.8795, Val Loss: 1.1752, Val Accuracy: 0.7366 Epoch 8966/10000, Train Loss: 1.0376, Train Accuracy: 0.8717, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 8967/10000, Train Loss: 1.0368, Train Accuracy: 0.8795, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 8968/10000, Train Loss: 1.0325, Train Accuracy: 0.8795, Val Loss: 1.1747, Val Accuracy: 0.7411 Epoch 8969/10000, Train Loss: 1.0337, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 8970/10000, Train Loss: 1.0412, Train Accuracy: 0.8739, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 8971/10000, Train Loss: 1.0411, Train Accuracy: 0.8694, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 8972/10000, Train Loss: 1.0331, Train Accuracy: 0.8739, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 8973/10000, Train Loss: 1.0414, Train Accuracy: 0.8683, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 8974/10000, Train Loss: 1.0340, Train Accuracy: 0.8761, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 8975/10000, Train Loss: 1.0466, Train Accuracy: 0.8672, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8976/10000, Train Loss: 1.0432, Train Accuracy: 0.8683, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 8977/10000, Train Loss: 1.0371, Train Accuracy: 0.8728, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8978/10000, Train Loss: 1.0380, Train Accuracy: 0.8728, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8979/10000, Train Loss: 1.0437, Train Accuracy: 0.8672, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8980/10000, Train Loss: 1.0338, Train Accuracy: 0.8839, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 8981/10000, Train Loss: 1.0363, Train Accuracy: 0.8761, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8982/10000, Train Loss: 1.0406, Train Accuracy: 0.8739, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8983/10000, Train Loss: 1.0511, Train Accuracy: 0.8616, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8984/10000, Train Loss: 1.0434, Train Accuracy: 0.8661, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8985/10000, Train Loss: 1.0387, Train Accuracy: 0.8739, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 8986/10000, Train Loss: 1.0347, Train Accuracy: 0.8795, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 8987/10000, Train Loss: 1.0447, Train Accuracy: 0.8705, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 8988/10000, Train Loss: 1.0350, Train Accuracy: 0.8772, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 8989/10000, Train Loss: 1.0368, Train Accuracy: 0.8750, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8990/10000, Train Loss: 1.0279, Train Accuracy: 0.8862, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 8991/10000, Train Loss: 1.0450, Train Accuracy: 0.8694, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 8992/10000, Train Loss: 1.0601, Train Accuracy: 0.8449, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 8993/10000, Train Loss: 1.0569, Train Accuracy: 0.8504, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 8994/10000, Train Loss: 1.0387, Train Accuracy: 0.8705, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 8995/10000, Train Loss: 1.0433, Train Accuracy: 0.8694, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 8996/10000, Train Loss: 1.0395, Train Accuracy: 0.8694, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 8997/10000, Train Loss: 1.0362, Train Accuracy: 0.8761, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 8998/10000, Train Loss: 1.0497, Train Accuracy: 0.8571, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 8999/10000, Train Loss: 1.0364, Train Accuracy: 0.8783, Val Loss: 1.1755, Val Accuracy: 0.7366 Epoch 9000/10000, Train Loss: 1.0457, Train Accuracy: 0.8672, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9001/10000, Train Loss: 1.0307, Train Accuracy: 0.8850, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 9002/10000, Train Loss: 1.0354, Train Accuracy: 0.8806, Val Loss: 1.1761, Val Accuracy: 0.7321 Epoch 9003/10000, Train Loss: 1.0302, Train Accuracy: 0.8850, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9004/10000, Train Loss: 1.0317, Train Accuracy: 0.8795, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9005/10000, Train Loss: 1.0301, Train Accuracy: 0.8895, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9006/10000, Train Loss: 1.0415, Train Accuracy: 0.8694, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9007/10000, Train Loss: 1.0505, Train Accuracy: 0.8549, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9008/10000, Train Loss: 1.0362, Train Accuracy: 0.8772, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9009/10000, Train Loss: 1.0352, Train Accuracy: 0.8806, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9010/10000, Train Loss: 1.0415, Train Accuracy: 0.8661, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9011/10000, Train Loss: 1.0469, Train Accuracy: 0.8627, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9012/10000, Train Loss: 1.0356, Train Accuracy: 0.8772, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9013/10000, Train Loss: 1.0362, Train Accuracy: 0.8772, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9014/10000, Train Loss: 1.0386, Train Accuracy: 0.8728, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 9015/10000, Train Loss: 1.0390, Train Accuracy: 0.8761, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 9016/10000, Train Loss: 1.0366, Train Accuracy: 0.8795, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9017/10000, Train Loss: 1.0302, Train Accuracy: 0.8806, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9018/10000, Train Loss: 1.0343, Train Accuracy: 0.8817, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9019/10000, Train Loss: 1.0515, Train Accuracy: 0.8605, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9020/10000, Train Loss: 1.0431, Train Accuracy: 0.8728, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9021/10000, Train Loss: 1.0421, Train Accuracy: 0.8717, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9022/10000, Train Loss: 1.0367, Train Accuracy: 0.8717, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 9023/10000, Train Loss: 1.0396, Train Accuracy: 0.8683, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9024/10000, Train Loss: 1.0456, Train Accuracy: 0.8672, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9025/10000, Train Loss: 1.0360, Train Accuracy: 0.8750, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 9026/10000, Train Loss: 1.0394, Train Accuracy: 0.8694, Val Loss: 1.1761, Val Accuracy: 0.7321 Epoch 9027/10000, Train Loss: 1.0421, Train Accuracy: 0.8650, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9028/10000, Train Loss: 1.0229, Train Accuracy: 0.8929, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9029/10000, Train Loss: 1.0435, Train Accuracy: 0.8672, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9030/10000, Train Loss: 1.0233, Train Accuracy: 0.8906, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9031/10000, Train Loss: 1.0421, Train Accuracy: 0.8694, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 9032/10000, Train Loss: 1.0279, Train Accuracy: 0.8828, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 9033/10000, Train Loss: 1.0422, Train Accuracy: 0.8594, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9034/10000, Train Loss: 1.0396, Train Accuracy: 0.8717, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9035/10000, Train Loss: 1.0469, Train Accuracy: 0.8627, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9036/10000, Train Loss: 1.0373, Train Accuracy: 0.8750, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9037/10000, Train Loss: 1.0467, Train Accuracy: 0.8583, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9038/10000, Train Loss: 1.0443, Train Accuracy: 0.8739, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9039/10000, Train Loss: 1.0535, Train Accuracy: 0.8549, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9040/10000, Train Loss: 1.0312, Train Accuracy: 0.8795, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 9041/10000, Train Loss: 1.0447, Train Accuracy: 0.8672, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9042/10000, Train Loss: 1.0439, Train Accuracy: 0.8638, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9043/10000, Train Loss: 1.0506, Train Accuracy: 0.8638, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9044/10000, Train Loss: 1.0406, Train Accuracy: 0.8672, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9045/10000, Train Loss: 1.0261, Train Accuracy: 0.8884, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9046/10000, Train Loss: 1.0430, Train Accuracy: 0.8661, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9047/10000, Train Loss: 1.0384, Train Accuracy: 0.8750, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9048/10000, Train Loss: 1.0456, Train Accuracy: 0.8638, Val Loss: 1.1762, Val Accuracy: 0.7277 Epoch 9049/10000, Train Loss: 1.0496, Train Accuracy: 0.8616, Val Loss: 1.1761, Val Accuracy: 0.7232 Epoch 9050/10000, Train Loss: 1.0398, Train Accuracy: 0.8683, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 9051/10000, Train Loss: 1.0298, Train Accuracy: 0.8839, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9052/10000, Train Loss: 1.0369, Train Accuracy: 0.8761, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9053/10000, Train Loss: 1.0397, Train Accuracy: 0.8705, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9054/10000, Train Loss: 1.0471, Train Accuracy: 0.8616, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9055/10000, Train Loss: 1.0363, Train Accuracy: 0.8717, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9056/10000, Train Loss: 1.0328, Train Accuracy: 0.8750, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9057/10000, Train Loss: 1.0304, Train Accuracy: 0.8783, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9058/10000, Train Loss: 1.0407, Train Accuracy: 0.8728, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9059/10000, Train Loss: 1.0410, Train Accuracy: 0.8783, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9060/10000, Train Loss: 1.0409, Train Accuracy: 0.8739, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9061/10000, Train Loss: 1.0336, Train Accuracy: 0.8817, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9062/10000, Train Loss: 1.0334, Train Accuracy: 0.8783, Val Loss: 1.1752, Val Accuracy: 0.7277 Epoch 9063/10000, Train Loss: 1.0398, Train Accuracy: 0.8672, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9064/10000, Train Loss: 1.0423, Train Accuracy: 0.8672, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9065/10000, Train Loss: 1.0373, Train Accuracy: 0.8728, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9066/10000, Train Loss: 1.0388, Train Accuracy: 0.8761, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9067/10000, Train Loss: 1.0303, Train Accuracy: 0.8873, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9068/10000, Train Loss: 1.0357, Train Accuracy: 0.8728, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9069/10000, Train Loss: 1.0424, Train Accuracy: 0.8739, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9070/10000, Train Loss: 1.0435, Train Accuracy: 0.8683, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9071/10000, Train Loss: 1.0331, Train Accuracy: 0.8761, Val Loss: 1.1739, Val Accuracy: 0.7366 Epoch 9072/10000, Train Loss: 1.0375, Train Accuracy: 0.8739, Val Loss: 1.1738, Val Accuracy: 0.7366 Epoch 9073/10000, Train Loss: 1.0370, Train Accuracy: 0.8728, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9074/10000, Train Loss: 1.0234, Train Accuracy: 0.8862, Val Loss: 1.1742, Val Accuracy: 0.7411 Epoch 9075/10000, Train Loss: 1.0403, Train Accuracy: 0.8661, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9076/10000, Train Loss: 1.0306, Train Accuracy: 0.8806, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9077/10000, Train Loss: 1.0364, Train Accuracy: 0.8750, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9078/10000, Train Loss: 1.0423, Train Accuracy: 0.8683, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9079/10000, Train Loss: 1.0371, Train Accuracy: 0.8739, Val Loss: 1.1747, Val Accuracy: 0.7411 Epoch 9080/10000, Train Loss: 1.0341, Train Accuracy: 0.8772, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9081/10000, Train Loss: 1.0339, Train Accuracy: 0.8705, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9082/10000, Train Loss: 1.0499, Train Accuracy: 0.8605, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9083/10000, Train Loss: 1.0528, Train Accuracy: 0.8594, Val Loss: 1.1740, Val Accuracy: 0.7411 Epoch 9084/10000, Train Loss: 1.0361, Train Accuracy: 0.8817, Val Loss: 1.1737, Val Accuracy: 0.7411 Epoch 9085/10000, Train Loss: 1.0343, Train Accuracy: 0.8772, Val Loss: 1.1736, Val Accuracy: 0.7411 Epoch 9086/10000, Train Loss: 1.0351, Train Accuracy: 0.8772, Val Loss: 1.1738, Val Accuracy: 0.7411 Epoch 9087/10000, Train Loss: 1.0484, Train Accuracy: 0.8650, Val Loss: 1.1740, Val Accuracy: 0.7411 Epoch 9088/10000, Train Loss: 1.0473, Train Accuracy: 0.8616, Val Loss: 1.1740, Val Accuracy: 0.7411 Epoch 9089/10000, Train Loss: 1.0341, Train Accuracy: 0.8783, Val Loss: 1.1739, Val Accuracy: 0.7366 Epoch 9090/10000, Train Loss: 1.0278, Train Accuracy: 0.8839, Val Loss: 1.1741, Val Accuracy: 0.7366 Epoch 9091/10000, Train Loss: 1.0309, Train Accuracy: 0.8806, Val Loss: 1.1742, Val Accuracy: 0.7366 Epoch 9092/10000, Train Loss: 1.0434, Train Accuracy: 0.8638, Val Loss: 1.1741, Val Accuracy: 0.7366 Epoch 9093/10000, Train Loss: 1.0310, Train Accuracy: 0.8862, Val Loss: 1.1741, Val Accuracy: 0.7366 Epoch 9094/10000, Train Loss: 1.0252, Train Accuracy: 0.8873, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9095/10000, Train Loss: 1.0342, Train Accuracy: 0.8839, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9096/10000, Train Loss: 1.0416, Train Accuracy: 0.8739, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9097/10000, Train Loss: 1.0212, Train Accuracy: 0.8973, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9098/10000, Train Loss: 1.0377, Train Accuracy: 0.8705, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9099/10000, Train Loss: 1.0447, Train Accuracy: 0.8616, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9100/10000, Train Loss: 1.0364, Train Accuracy: 0.8705, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9101/10000, Train Loss: 1.0450, Train Accuracy: 0.8627, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9102/10000, Train Loss: 1.0303, Train Accuracy: 0.8873, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9103/10000, Train Loss: 1.0329, Train Accuracy: 0.8828, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9104/10000, Train Loss: 1.0257, Train Accuracy: 0.8929, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9105/10000, Train Loss: 1.0451, Train Accuracy: 0.8705, Val Loss: 1.1752, Val Accuracy: 0.7366 Epoch 9106/10000, Train Loss: 1.0475, Train Accuracy: 0.8672, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9107/10000, Train Loss: 1.0378, Train Accuracy: 0.8739, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9108/10000, Train Loss: 1.0415, Train Accuracy: 0.8683, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9109/10000, Train Loss: 1.0390, Train Accuracy: 0.8739, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9110/10000, Train Loss: 1.0318, Train Accuracy: 0.8862, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9111/10000, Train Loss: 1.0493, Train Accuracy: 0.8571, Val Loss: 1.1745, Val Accuracy: 0.7411 Epoch 9112/10000, Train Loss: 1.0345, Train Accuracy: 0.8806, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9113/10000, Train Loss: 1.0384, Train Accuracy: 0.8795, Val Loss: 1.1748, Val Accuracy: 0.7411 Epoch 9114/10000, Train Loss: 1.0298, Train Accuracy: 0.8806, Val Loss: 1.1749, Val Accuracy: 0.7411 Epoch 9115/10000, Train Loss: 1.0496, Train Accuracy: 0.8571, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9116/10000, Train Loss: 1.0387, Train Accuracy: 0.8795, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9117/10000, Train Loss: 1.0299, Train Accuracy: 0.8850, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9118/10000, Train Loss: 1.0340, Train Accuracy: 0.8783, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9119/10000, Train Loss: 1.0327, Train Accuracy: 0.8806, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9120/10000, Train Loss: 1.0484, Train Accuracy: 0.8583, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9121/10000, Train Loss: 1.0479, Train Accuracy: 0.8616, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9122/10000, Train Loss: 1.0374, Train Accuracy: 0.8728, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9123/10000, Train Loss: 1.0370, Train Accuracy: 0.8761, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9124/10000, Train Loss: 1.0387, Train Accuracy: 0.8717, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9125/10000, Train Loss: 1.0471, Train Accuracy: 0.8616, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9126/10000, Train Loss: 1.0334, Train Accuracy: 0.8817, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9127/10000, Train Loss: 1.0385, Train Accuracy: 0.8705, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9128/10000, Train Loss: 1.0372, Train Accuracy: 0.8795, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9129/10000, Train Loss: 1.0349, Train Accuracy: 0.8795, Val Loss: 1.1745, Val Accuracy: 0.7411 Epoch 9130/10000, Train Loss: 1.0271, Train Accuracy: 0.8806, Val Loss: 1.1741, Val Accuracy: 0.7411 Epoch 9131/10000, Train Loss: 1.0418, Train Accuracy: 0.8728, Val Loss: 1.1743, Val Accuracy: 0.7411 Epoch 9132/10000, Train Loss: 1.0410, Train Accuracy: 0.8683, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9133/10000, Train Loss: 1.0292, Train Accuracy: 0.8862, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9134/10000, Train Loss: 1.0546, Train Accuracy: 0.8560, Val Loss: 1.1746, Val Accuracy: 0.7411 Epoch 9135/10000, Train Loss: 1.0412, Train Accuracy: 0.8761, Val Loss: 1.1745, Val Accuracy: 0.7411 Epoch 9136/10000, Train Loss: 1.0466, Train Accuracy: 0.8638, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9137/10000, Train Loss: 1.0415, Train Accuracy: 0.8583, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9138/10000, Train Loss: 1.0359, Train Accuracy: 0.8783, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9139/10000, Train Loss: 1.0302, Train Accuracy: 0.8884, Val Loss: 1.1743, Val Accuracy: 0.7411 Epoch 9140/10000, Train Loss: 1.0394, Train Accuracy: 0.8705, Val Loss: 1.1741, Val Accuracy: 0.7411 Epoch 9141/10000, Train Loss: 1.0445, Train Accuracy: 0.8616, Val Loss: 1.1741, Val Accuracy: 0.7411 Epoch 9142/10000, Train Loss: 1.0392, Train Accuracy: 0.8728, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9143/10000, Train Loss: 1.0379, Train Accuracy: 0.8728, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9144/10000, Train Loss: 1.0370, Train Accuracy: 0.8694, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9145/10000, Train Loss: 1.0338, Train Accuracy: 0.8728, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9146/10000, Train Loss: 1.0465, Train Accuracy: 0.8549, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9147/10000, Train Loss: 1.0410, Train Accuracy: 0.8650, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9148/10000, Train Loss: 1.0439, Train Accuracy: 0.8616, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9149/10000, Train Loss: 1.0519, Train Accuracy: 0.8594, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9150/10000, Train Loss: 1.0362, Train Accuracy: 0.8750, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9151/10000, Train Loss: 1.0346, Train Accuracy: 0.8795, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9152/10000, Train Loss: 1.0311, Train Accuracy: 0.8795, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9153/10000, Train Loss: 1.0243, Train Accuracy: 0.8862, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9154/10000, Train Loss: 1.0418, Train Accuracy: 0.8739, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9155/10000, Train Loss: 1.0468, Train Accuracy: 0.8650, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9156/10000, Train Loss: 1.0416, Train Accuracy: 0.8717, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9157/10000, Train Loss: 1.0248, Train Accuracy: 0.8862, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9158/10000, Train Loss: 1.0423, Train Accuracy: 0.8728, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9159/10000, Train Loss: 1.0398, Train Accuracy: 0.8717, Val Loss: 1.1747, Val Accuracy: 0.7411 Epoch 9160/10000, Train Loss: 1.0274, Train Accuracy: 0.8839, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9161/10000, Train Loss: 1.0362, Train Accuracy: 0.8783, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 9162/10000, Train Loss: 1.0342, Train Accuracy: 0.8806, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9163/10000, Train Loss: 1.0330, Train Accuracy: 0.8783, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9164/10000, Train Loss: 1.0241, Train Accuracy: 0.8884, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9165/10000, Train Loss: 1.0211, Train Accuracy: 0.8940, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9166/10000, Train Loss: 1.0385, Train Accuracy: 0.8705, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9167/10000, Train Loss: 1.0354, Train Accuracy: 0.8750, Val Loss: 1.1747, Val Accuracy: 0.7411 Epoch 9168/10000, Train Loss: 1.0418, Train Accuracy: 0.8705, Val Loss: 1.1745, Val Accuracy: 0.7411 Epoch 9169/10000, Train Loss: 1.0334, Train Accuracy: 0.8806, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9170/10000, Train Loss: 1.0387, Train Accuracy: 0.8739, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9171/10000, Train Loss: 1.0325, Train Accuracy: 0.8761, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9172/10000, Train Loss: 1.0366, Train Accuracy: 0.8739, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9173/10000, Train Loss: 1.0395, Train Accuracy: 0.8717, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9174/10000, Train Loss: 1.0269, Train Accuracy: 0.8839, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9175/10000, Train Loss: 1.0356, Train Accuracy: 0.8739, Val Loss: 1.1746, Val Accuracy: 0.7411 Epoch 9176/10000, Train Loss: 1.0363, Train Accuracy: 0.8850, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9177/10000, Train Loss: 1.0353, Train Accuracy: 0.8728, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 9178/10000, Train Loss: 1.0392, Train Accuracy: 0.8806, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9179/10000, Train Loss: 1.0331, Train Accuracy: 0.8739, Val Loss: 1.1742, Val Accuracy: 0.7366 Epoch 9180/10000, Train Loss: 1.0399, Train Accuracy: 0.8683, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9181/10000, Train Loss: 1.0254, Train Accuracy: 0.8862, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9182/10000, Train Loss: 1.0246, Train Accuracy: 0.8873, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9183/10000, Train Loss: 1.0340, Train Accuracy: 0.8750, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9184/10000, Train Loss: 1.0357, Train Accuracy: 0.8795, Val Loss: 1.1744, Val Accuracy: 0.7411 Epoch 9185/10000, Train Loss: 1.0391, Train Accuracy: 0.8683, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9186/10000, Train Loss: 1.0388, Train Accuracy: 0.8683, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9187/10000, Train Loss: 1.0396, Train Accuracy: 0.8728, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9188/10000, Train Loss: 1.0375, Train Accuracy: 0.8739, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9189/10000, Train Loss: 1.0306, Train Accuracy: 0.8761, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9190/10000, Train Loss: 1.0319, Train Accuracy: 0.8772, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9191/10000, Train Loss: 1.0293, Train Accuracy: 0.8862, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9192/10000, Train Loss: 1.0361, Train Accuracy: 0.8717, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9193/10000, Train Loss: 1.0262, Train Accuracy: 0.8873, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 9194/10000, Train Loss: 1.0270, Train Accuracy: 0.8850, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9195/10000, Train Loss: 1.0394, Train Accuracy: 0.8683, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9196/10000, Train Loss: 1.0402, Train Accuracy: 0.8683, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9197/10000, Train Loss: 1.0366, Train Accuracy: 0.8806, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9198/10000, Train Loss: 1.0467, Train Accuracy: 0.8627, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9199/10000, Train Loss: 1.0329, Train Accuracy: 0.8739, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9200/10000, Train Loss: 1.0371, Train Accuracy: 0.8750, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9201/10000, Train Loss: 1.0340, Train Accuracy: 0.8739, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9202/10000, Train Loss: 1.0421, Train Accuracy: 0.8661, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9203/10000, Train Loss: 1.0388, Train Accuracy: 0.8761, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9204/10000, Train Loss: 1.0318, Train Accuracy: 0.8806, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9205/10000, Train Loss: 1.0462, Train Accuracy: 0.8683, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9206/10000, Train Loss: 1.0297, Train Accuracy: 0.8761, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9207/10000, Train Loss: 1.0374, Train Accuracy: 0.8728, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9208/10000, Train Loss: 1.0337, Train Accuracy: 0.8783, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9209/10000, Train Loss: 1.0470, Train Accuracy: 0.8650, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9210/10000, Train Loss: 1.0345, Train Accuracy: 0.8817, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9211/10000, Train Loss: 1.0326, Train Accuracy: 0.8783, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9212/10000, Train Loss: 1.0444, Train Accuracy: 0.8750, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9213/10000, Train Loss: 1.0327, Train Accuracy: 0.8839, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9214/10000, Train Loss: 1.0354, Train Accuracy: 0.8761, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9215/10000, Train Loss: 1.0347, Train Accuracy: 0.8717, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9216/10000, Train Loss: 1.0444, Train Accuracy: 0.8661, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9217/10000, Train Loss: 1.0353, Train Accuracy: 0.8739, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9218/10000, Train Loss: 1.0409, Train Accuracy: 0.8672, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9219/10000, Train Loss: 1.0391, Train Accuracy: 0.8694, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9220/10000, Train Loss: 1.0340, Train Accuracy: 0.8739, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9221/10000, Train Loss: 1.0300, Train Accuracy: 0.8772, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9222/10000, Train Loss: 1.0360, Train Accuracy: 0.8750, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9223/10000, Train Loss: 1.0381, Train Accuracy: 0.8739, Val Loss: 1.1741, Val Accuracy: 0.7366 Epoch 9224/10000, Train Loss: 1.0451, Train Accuracy: 0.8605, Val Loss: 1.1742, Val Accuracy: 0.7366 Epoch 9225/10000, Train Loss: 1.0399, Train Accuracy: 0.8683, Val Loss: 1.1745, Val Accuracy: 0.7366 Epoch 9226/10000, Train Loss: 1.0416, Train Accuracy: 0.8705, Val Loss: 1.1746, Val Accuracy: 0.7366 Epoch 9227/10000, Train Loss: 1.0314, Train Accuracy: 0.8850, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9228/10000, Train Loss: 1.0435, Train Accuracy: 0.8616, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9229/10000, Train Loss: 1.0304, Train Accuracy: 0.8817, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9230/10000, Train Loss: 1.0469, Train Accuracy: 0.8571, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9231/10000, Train Loss: 1.0351, Train Accuracy: 0.8761, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9232/10000, Train Loss: 1.0362, Train Accuracy: 0.8772, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9233/10000, Train Loss: 1.0392, Train Accuracy: 0.8683, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9234/10000, Train Loss: 1.0365, Train Accuracy: 0.8750, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9235/10000, Train Loss: 1.0500, Train Accuracy: 0.8571, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9236/10000, Train Loss: 1.0296, Train Accuracy: 0.8750, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9237/10000, Train Loss: 1.0205, Train Accuracy: 0.8862, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9238/10000, Train Loss: 1.0292, Train Accuracy: 0.8862, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9239/10000, Train Loss: 1.0522, Train Accuracy: 0.8638, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9240/10000, Train Loss: 1.0334, Train Accuracy: 0.8772, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 9241/10000, Train Loss: 1.0265, Train Accuracy: 0.8839, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9242/10000, Train Loss: 1.0364, Train Accuracy: 0.8772, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9243/10000, Train Loss: 1.0309, Train Accuracy: 0.8828, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9244/10000, Train Loss: 1.0441, Train Accuracy: 0.8705, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9245/10000, Train Loss: 1.0351, Train Accuracy: 0.8739, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9246/10000, Train Loss: 1.0434, Train Accuracy: 0.8672, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9247/10000, Train Loss: 1.0372, Train Accuracy: 0.8705, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9248/10000, Train Loss: 1.0477, Train Accuracy: 0.8594, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9249/10000, Train Loss: 1.0367, Train Accuracy: 0.8728, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9250/10000, Train Loss: 1.0427, Train Accuracy: 0.8683, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9251/10000, Train Loss: 1.0289, Train Accuracy: 0.8783, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9252/10000, Train Loss: 1.0253, Train Accuracy: 0.8895, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9253/10000, Train Loss: 1.0336, Train Accuracy: 0.8783, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9254/10000, Train Loss: 1.0303, Train Accuracy: 0.8828, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9255/10000, Train Loss: 1.0324, Train Accuracy: 0.8783, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9256/10000, Train Loss: 1.0294, Train Accuracy: 0.8884, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9257/10000, Train Loss: 1.0405, Train Accuracy: 0.8717, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9258/10000, Train Loss: 1.0465, Train Accuracy: 0.8627, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9259/10000, Train Loss: 1.0416, Train Accuracy: 0.8650, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9260/10000, Train Loss: 1.0327, Train Accuracy: 0.8795, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9261/10000, Train Loss: 1.0330, Train Accuracy: 0.8750, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9262/10000, Train Loss: 1.0312, Train Accuracy: 0.8761, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9263/10000, Train Loss: 1.0322, Train Accuracy: 0.8783, Val Loss: 1.1754, Val Accuracy: 0.7232 Epoch 9264/10000, Train Loss: 1.0197, Train Accuracy: 0.8973, Val Loss: 1.1753, Val Accuracy: 0.7232 Epoch 9265/10000, Train Loss: 1.0410, Train Accuracy: 0.8694, Val Loss: 1.1754, Val Accuracy: 0.7232 Epoch 9266/10000, Train Loss: 1.0236, Train Accuracy: 0.8884, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9267/10000, Train Loss: 1.0280, Train Accuracy: 0.8817, Val Loss: 1.1761, Val Accuracy: 0.7232 Epoch 9268/10000, Train Loss: 1.0362, Train Accuracy: 0.8750, Val Loss: 1.1764, Val Accuracy: 0.7232 Epoch 9269/10000, Train Loss: 1.0279, Train Accuracy: 0.8839, Val Loss: 1.1761, Val Accuracy: 0.7232 Epoch 9270/10000, Train Loss: 1.0305, Train Accuracy: 0.8850, Val Loss: 1.1762, Val Accuracy: 0.7232 Epoch 9271/10000, Train Loss: 1.0313, Train Accuracy: 0.8839, Val Loss: 1.1764, Val Accuracy: 0.7232 Epoch 9272/10000, Train Loss: 1.0281, Train Accuracy: 0.8862, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 9273/10000, Train Loss: 1.0315, Train Accuracy: 0.8850, Val Loss: 1.1762, Val Accuracy: 0.7277 Epoch 9274/10000, Train Loss: 1.0247, Train Accuracy: 0.8850, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9275/10000, Train Loss: 1.0269, Train Accuracy: 0.8850, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9276/10000, Train Loss: 1.0270, Train Accuracy: 0.8828, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9277/10000, Train Loss: 1.0369, Train Accuracy: 0.8717, Val Loss: 1.1763, Val Accuracy: 0.7232 Epoch 9278/10000, Train Loss: 1.0438, Train Accuracy: 0.8683, Val Loss: 1.1763, Val Accuracy: 0.7232 Epoch 9279/10000, Train Loss: 1.0314, Train Accuracy: 0.8828, Val Loss: 1.1764, Val Accuracy: 0.7232 Epoch 9280/10000, Train Loss: 1.0435, Train Accuracy: 0.8638, Val Loss: 1.1765, Val Accuracy: 0.7232 Epoch 9281/10000, Train Loss: 1.0414, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7232 Epoch 9282/10000, Train Loss: 1.0227, Train Accuracy: 0.8873, Val Loss: 1.1764, Val Accuracy: 0.7232 Epoch 9283/10000, Train Loss: 1.0208, Train Accuracy: 0.8973, Val Loss: 1.1765, Val Accuracy: 0.7232 Epoch 9284/10000, Train Loss: 1.0354, Train Accuracy: 0.8772, Val Loss: 1.1766, Val Accuracy: 0.7232 Epoch 9285/10000, Train Loss: 1.0343, Train Accuracy: 0.8783, Val Loss: 1.1767, Val Accuracy: 0.7232 Epoch 9286/10000, Train Loss: 1.0471, Train Accuracy: 0.8571, Val Loss: 1.1767, Val Accuracy: 0.7232 Epoch 9287/10000, Train Loss: 1.0315, Train Accuracy: 0.8750, Val Loss: 1.1769, Val Accuracy: 0.7232 Epoch 9288/10000, Train Loss: 1.0387, Train Accuracy: 0.8739, Val Loss: 1.1768, Val Accuracy: 0.7232 Epoch 9289/10000, Train Loss: 1.0309, Train Accuracy: 0.8705, Val Loss: 1.1772, Val Accuracy: 0.7232 Epoch 9290/10000, Train Loss: 1.0481, Train Accuracy: 0.8661, Val Loss: 1.1775, Val Accuracy: 0.7232 Epoch 9291/10000, Train Loss: 1.0377, Train Accuracy: 0.8717, Val Loss: 1.1777, Val Accuracy: 0.7232 Epoch 9292/10000, Train Loss: 1.0496, Train Accuracy: 0.8616, Val Loss: 1.1772, Val Accuracy: 0.7232 Epoch 9293/10000, Train Loss: 1.0289, Train Accuracy: 0.8850, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9294/10000, Train Loss: 1.0266, Train Accuracy: 0.8862, Val Loss: 1.1776, Val Accuracy: 0.7232 Epoch 9295/10000, Train Loss: 1.0314, Train Accuracy: 0.8817, Val Loss: 1.1775, Val Accuracy: 0.7232 Epoch 9296/10000, Train Loss: 1.0394, Train Accuracy: 0.8761, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9297/10000, Train Loss: 1.0468, Train Accuracy: 0.8683, Val Loss: 1.1776, Val Accuracy: 0.7232 Epoch 9298/10000, Train Loss: 1.0276, Train Accuracy: 0.8895, Val Loss: 1.1776, Val Accuracy: 0.7232 Epoch 9299/10000, Train Loss: 1.0398, Train Accuracy: 0.8672, Val Loss: 1.1778, Val Accuracy: 0.7232 Epoch 9300/10000, Train Loss: 1.0455, Train Accuracy: 0.8616, Val Loss: 1.1772, Val Accuracy: 0.7232 Epoch 9301/10000, Train Loss: 1.0313, Train Accuracy: 0.8795, Val Loss: 1.1773, Val Accuracy: 0.7232 Epoch 9302/10000, Train Loss: 1.0371, Train Accuracy: 0.8783, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9303/10000, Train Loss: 1.0388, Train Accuracy: 0.8694, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9304/10000, Train Loss: 1.0283, Train Accuracy: 0.8917, Val Loss: 1.1773, Val Accuracy: 0.7232 Epoch 9305/10000, Train Loss: 1.0418, Train Accuracy: 0.8672, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9306/10000, Train Loss: 1.0485, Train Accuracy: 0.8571, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9307/10000, Train Loss: 1.0379, Train Accuracy: 0.8705, Val Loss: 1.1775, Val Accuracy: 0.7232 Epoch 9308/10000, Train Loss: 1.0360, Train Accuracy: 0.8739, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9309/10000, Train Loss: 1.0389, Train Accuracy: 0.8683, Val Loss: 1.1775, Val Accuracy: 0.7232 Epoch 9310/10000, Train Loss: 1.0390, Train Accuracy: 0.8728, Val Loss: 1.1774, Val Accuracy: 0.7232 Epoch 9311/10000, Train Loss: 1.0355, Train Accuracy: 0.8761, Val Loss: 1.1773, Val Accuracy: 0.7232 Epoch 9312/10000, Train Loss: 1.0322, Train Accuracy: 0.8795, Val Loss: 1.1776, Val Accuracy: 0.7232 Epoch 9313/10000, Train Loss: 1.0382, Train Accuracy: 0.8750, Val Loss: 1.1779, Val Accuracy: 0.7277 Epoch 9314/10000, Train Loss: 1.0404, Train Accuracy: 0.8694, Val Loss: 1.1777, Val Accuracy: 0.7277 Epoch 9315/10000, Train Loss: 1.0352, Train Accuracy: 0.8683, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 9316/10000, Train Loss: 1.0236, Train Accuracy: 0.8895, Val Loss: 1.1775, Val Accuracy: 0.7277 Epoch 9317/10000, Train Loss: 1.0402, Train Accuracy: 0.8750, Val Loss: 1.1777, Val Accuracy: 0.7232 Epoch 9318/10000, Train Loss: 1.0378, Train Accuracy: 0.8717, Val Loss: 1.1778, Val Accuracy: 0.7232 Epoch 9319/10000, Train Loss: 1.0293, Train Accuracy: 0.8806, Val Loss: 1.1775, Val Accuracy: 0.7188 Epoch 9320/10000, Train Loss: 1.0305, Train Accuracy: 0.8772, Val Loss: 1.1772, Val Accuracy: 0.7232 Epoch 9321/10000, Train Loss: 1.0449, Train Accuracy: 0.8694, Val Loss: 1.1772, Val Accuracy: 0.7232 Epoch 9322/10000, Train Loss: 1.0301, Train Accuracy: 0.8873, Val Loss: 1.1767, Val Accuracy: 0.7277 Epoch 9323/10000, Train Loss: 1.0456, Train Accuracy: 0.8750, Val Loss: 1.1767, Val Accuracy: 0.7277 Epoch 9324/10000, Train Loss: 1.0395, Train Accuracy: 0.8650, Val Loss: 1.1765, Val Accuracy: 0.7277 Epoch 9325/10000, Train Loss: 1.0324, Train Accuracy: 0.8705, Val Loss: 1.1767, Val Accuracy: 0.7277 Epoch 9326/10000, Train Loss: 1.0293, Train Accuracy: 0.8761, Val Loss: 1.1770, Val Accuracy: 0.7277 Epoch 9327/10000, Train Loss: 1.0281, Train Accuracy: 0.8862, Val Loss: 1.1774, Val Accuracy: 0.7277 Epoch 9328/10000, Train Loss: 1.0389, Train Accuracy: 0.8683, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 9329/10000, Train Loss: 1.0400, Train Accuracy: 0.8705, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 9330/10000, Train Loss: 1.0384, Train Accuracy: 0.8694, Val Loss: 1.1767, Val Accuracy: 0.7277 Epoch 9331/10000, Train Loss: 1.0304, Train Accuracy: 0.8806, Val Loss: 1.1767, Val Accuracy: 0.7277 Epoch 9332/10000, Train Loss: 1.0286, Train Accuracy: 0.8884, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 9333/10000, Train Loss: 1.0406, Train Accuracy: 0.8750, Val Loss: 1.1767, Val Accuracy: 0.7277 Epoch 9334/10000, Train Loss: 1.0298, Train Accuracy: 0.8750, Val Loss: 1.1770, Val Accuracy: 0.7277 Epoch 9335/10000, Train Loss: 1.0401, Train Accuracy: 0.8739, Val Loss: 1.1772, Val Accuracy: 0.7277 Epoch 9336/10000, Train Loss: 1.0300, Train Accuracy: 0.8795, Val Loss: 1.1769, Val Accuracy: 0.7277 Epoch 9337/10000, Train Loss: 1.0310, Train Accuracy: 0.8828, Val Loss: 1.1766, Val Accuracy: 0.7277 Epoch 9338/10000, Train Loss: 1.0434, Train Accuracy: 0.8683, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 9339/10000, Train Loss: 1.0287, Train Accuracy: 0.8828, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9340/10000, Train Loss: 1.0208, Train Accuracy: 0.8940, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9341/10000, Train Loss: 1.0226, Train Accuracy: 0.8917, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9342/10000, Train Loss: 1.0308, Train Accuracy: 0.8839, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9343/10000, Train Loss: 1.0417, Train Accuracy: 0.8705, Val Loss: 1.1756, Val Accuracy: 0.7277 Epoch 9344/10000, Train Loss: 1.0349, Train Accuracy: 0.8739, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9345/10000, Train Loss: 1.0260, Train Accuracy: 0.8839, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9346/10000, Train Loss: 1.0286, Train Accuracy: 0.8817, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9347/10000, Train Loss: 1.0248, Train Accuracy: 0.8951, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9348/10000, Train Loss: 1.0345, Train Accuracy: 0.8717, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9349/10000, Train Loss: 1.0384, Train Accuracy: 0.8761, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9350/10000, Train Loss: 1.0377, Train Accuracy: 0.8761, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9351/10000, Train Loss: 1.0432, Train Accuracy: 0.8717, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9352/10000, Train Loss: 1.0278, Train Accuracy: 0.8884, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9353/10000, Train Loss: 1.0377, Train Accuracy: 0.8705, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9354/10000, Train Loss: 1.0257, Train Accuracy: 0.8929, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9355/10000, Train Loss: 1.0443, Train Accuracy: 0.8661, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9356/10000, Train Loss: 1.0392, Train Accuracy: 0.8694, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9357/10000, Train Loss: 1.0420, Train Accuracy: 0.8717, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9358/10000, Train Loss: 1.0177, Train Accuracy: 0.9007, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9359/10000, Train Loss: 1.0287, Train Accuracy: 0.8761, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9360/10000, Train Loss: 1.0407, Train Accuracy: 0.8717, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9361/10000, Train Loss: 1.0231, Train Accuracy: 0.8828, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 9362/10000, Train Loss: 1.0221, Train Accuracy: 0.8895, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9363/10000, Train Loss: 1.0305, Train Accuracy: 0.8850, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9364/10000, Train Loss: 1.0412, Train Accuracy: 0.8705, Val Loss: 1.1762, Val Accuracy: 0.7277 Epoch 9365/10000, Train Loss: 1.0321, Train Accuracy: 0.8761, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9366/10000, Train Loss: 1.0431, Train Accuracy: 0.8616, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9367/10000, Train Loss: 1.0267, Train Accuracy: 0.8884, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9368/10000, Train Loss: 1.0236, Train Accuracy: 0.8884, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9369/10000, Train Loss: 1.0330, Train Accuracy: 0.8806, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 9370/10000, Train Loss: 1.0303, Train Accuracy: 0.8717, Val Loss: 1.1763, Val Accuracy: 0.7277 Epoch 9371/10000, Train Loss: 1.0314, Train Accuracy: 0.8817, Val Loss: 1.1764, Val Accuracy: 0.7277 Epoch 9372/10000, Train Loss: 1.0241, Train Accuracy: 0.8873, Val Loss: 1.1762, Val Accuracy: 0.7277 Epoch 9373/10000, Train Loss: 1.0354, Train Accuracy: 0.8817, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9374/10000, Train Loss: 1.0345, Train Accuracy: 0.8739, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9375/10000, Train Loss: 1.0199, Train Accuracy: 0.8951, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9376/10000, Train Loss: 1.0286, Train Accuracy: 0.8850, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9377/10000, Train Loss: 1.0289, Train Accuracy: 0.8850, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 9378/10000, Train Loss: 1.0351, Train Accuracy: 0.8761, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 9379/10000, Train Loss: 1.0248, Train Accuracy: 0.8850, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 9380/10000, Train Loss: 1.0431, Train Accuracy: 0.8728, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 9381/10000, Train Loss: 1.0360, Train Accuracy: 0.8772, Val Loss: 1.1765, Val Accuracy: 0.7277 Epoch 9382/10000, Train Loss: 1.0316, Train Accuracy: 0.8795, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 9383/10000, Train Loss: 1.0377, Train Accuracy: 0.8772, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 9384/10000, Train Loss: 1.0443, Train Accuracy: 0.8594, Val Loss: 1.1768, Val Accuracy: 0.7321 Epoch 9385/10000, Train Loss: 1.0332, Train Accuracy: 0.8772, Val Loss: 1.1766, Val Accuracy: 0.7277 Epoch 9386/10000, Train Loss: 1.0328, Train Accuracy: 0.8783, Val Loss: 1.1766, Val Accuracy: 0.7321 Epoch 9387/10000, Train Loss: 1.0389, Train Accuracy: 0.8717, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9388/10000, Train Loss: 1.0327, Train Accuracy: 0.8795, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9389/10000, Train Loss: 1.0262, Train Accuracy: 0.8917, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9390/10000, Train Loss: 1.0240, Train Accuracy: 0.8895, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9391/10000, Train Loss: 1.0246, Train Accuracy: 0.8873, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9392/10000, Train Loss: 1.0357, Train Accuracy: 0.8705, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9393/10000, Train Loss: 1.0332, Train Accuracy: 0.8783, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9394/10000, Train Loss: 1.0269, Train Accuracy: 0.8862, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9395/10000, Train Loss: 1.0381, Train Accuracy: 0.8683, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9396/10000, Train Loss: 1.0363, Train Accuracy: 0.8761, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9397/10000, Train Loss: 1.0255, Train Accuracy: 0.8873, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9398/10000, Train Loss: 1.0387, Train Accuracy: 0.8728, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9399/10000, Train Loss: 1.0320, Train Accuracy: 0.8806, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9400/10000, Train Loss: 1.0241, Train Accuracy: 0.8895, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9401/10000, Train Loss: 1.0350, Train Accuracy: 0.8728, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9402/10000, Train Loss: 1.0285, Train Accuracy: 0.8839, Val Loss: 1.1762, Val Accuracy: 0.7321 Epoch 9403/10000, Train Loss: 1.0373, Train Accuracy: 0.8694, Val Loss: 1.1762, Val Accuracy: 0.7277 Epoch 9404/10000, Train Loss: 1.0322, Train Accuracy: 0.8783, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9405/10000, Train Loss: 1.0318, Train Accuracy: 0.8783, Val Loss: 1.1761, Val Accuracy: 0.7277 Epoch 9406/10000, Train Loss: 1.0459, Train Accuracy: 0.8705, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9407/10000, Train Loss: 1.0292, Train Accuracy: 0.8828, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9408/10000, Train Loss: 1.0329, Train Accuracy: 0.8761, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9409/10000, Train Loss: 1.0196, Train Accuracy: 0.8917, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9410/10000, Train Loss: 1.0258, Train Accuracy: 0.8873, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 9411/10000, Train Loss: 1.0276, Train Accuracy: 0.8873, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9412/10000, Train Loss: 1.0197, Train Accuracy: 0.8895, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9413/10000, Train Loss: 1.0356, Train Accuracy: 0.8705, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 9414/10000, Train Loss: 1.0282, Train Accuracy: 0.8839, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9415/10000, Train Loss: 1.0238, Train Accuracy: 0.8906, Val Loss: 1.1761, Val Accuracy: 0.7321 Epoch 9416/10000, Train Loss: 1.0204, Train Accuracy: 0.8940, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9417/10000, Train Loss: 1.0302, Train Accuracy: 0.8828, Val Loss: 1.1758, Val Accuracy: 0.7321 Epoch 9418/10000, Train Loss: 1.0257, Train Accuracy: 0.8850, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9419/10000, Train Loss: 1.0357, Train Accuracy: 0.8739, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9420/10000, Train Loss: 1.0323, Train Accuracy: 0.8850, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 9421/10000, Train Loss: 1.0302, Train Accuracy: 0.8850, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9422/10000, Train Loss: 1.0289, Train Accuracy: 0.8828, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9423/10000, Train Loss: 1.0183, Train Accuracy: 0.8895, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9424/10000, Train Loss: 1.0232, Train Accuracy: 0.8895, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9425/10000, Train Loss: 1.0171, Train Accuracy: 0.8884, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9426/10000, Train Loss: 1.0479, Train Accuracy: 0.8594, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9427/10000, Train Loss: 1.0303, Train Accuracy: 0.8817, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9428/10000, Train Loss: 1.0369, Train Accuracy: 0.8739, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9429/10000, Train Loss: 1.0296, Train Accuracy: 0.8795, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9430/10000, Train Loss: 1.0226, Train Accuracy: 0.8895, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9431/10000, Train Loss: 1.0231, Train Accuracy: 0.8895, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9432/10000, Train Loss: 1.0253, Train Accuracy: 0.8850, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9433/10000, Train Loss: 1.0325, Train Accuracy: 0.8806, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9434/10000, Train Loss: 1.0276, Train Accuracy: 0.8873, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9435/10000, Train Loss: 1.0347, Train Accuracy: 0.8739, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9436/10000, Train Loss: 1.0372, Train Accuracy: 0.8672, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9437/10000, Train Loss: 1.0360, Train Accuracy: 0.8750, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9438/10000, Train Loss: 1.0283, Train Accuracy: 0.8783, Val Loss: 1.1760, Val Accuracy: 0.7277 Epoch 9439/10000, Train Loss: 1.0343, Train Accuracy: 0.8717, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9440/10000, Train Loss: 1.0277, Train Accuracy: 0.8828, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9441/10000, Train Loss: 1.0452, Train Accuracy: 0.8605, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 9442/10000, Train Loss: 1.0268, Train Accuracy: 0.8828, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 9443/10000, Train Loss: 1.0306, Train Accuracy: 0.8783, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9444/10000, Train Loss: 1.0411, Train Accuracy: 0.8650, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9445/10000, Train Loss: 1.0353, Train Accuracy: 0.8783, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9446/10000, Train Loss: 1.0207, Train Accuracy: 0.8873, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9447/10000, Train Loss: 1.0395, Train Accuracy: 0.8717, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9448/10000, Train Loss: 1.0296, Train Accuracy: 0.8795, Val Loss: 1.1758, Val Accuracy: 0.7366 Epoch 9449/10000, Train Loss: 1.0354, Train Accuracy: 0.8694, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 9450/10000, Train Loss: 1.0340, Train Accuracy: 0.8817, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9451/10000, Train Loss: 1.0357, Train Accuracy: 0.8817, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9452/10000, Train Loss: 1.0281, Train Accuracy: 0.8873, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9453/10000, Train Loss: 1.0358, Train Accuracy: 0.8750, Val Loss: 1.1757, Val Accuracy: 0.7366 Epoch 9454/10000, Train Loss: 1.0236, Train Accuracy: 0.8895, Val Loss: 1.1756, Val Accuracy: 0.7366 Epoch 9455/10000, Train Loss: 1.0222, Train Accuracy: 0.8906, Val Loss: 1.1760, Val Accuracy: 0.7321 Epoch 9456/10000, Train Loss: 1.0278, Train Accuracy: 0.8806, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 9457/10000, Train Loss: 1.0304, Train Accuracy: 0.8839, Val Loss: 1.1764, Val Accuracy: 0.7366 Epoch 9458/10000, Train Loss: 1.0347, Train Accuracy: 0.8783, Val Loss: 1.1765, Val Accuracy: 0.7321 Epoch 9459/10000, Train Loss: 1.0240, Train Accuracy: 0.8839, Val Loss: 1.1763, Val Accuracy: 0.7321 Epoch 9460/10000, Train Loss: 1.0300, Train Accuracy: 0.8828, Val Loss: 1.1761, Val Accuracy: 0.7366 Epoch 9461/10000, Train Loss: 1.0306, Train Accuracy: 0.8873, Val Loss: 1.1763, Val Accuracy: 0.7366 Epoch 9462/10000, Train Loss: 1.0328, Train Accuracy: 0.8728, Val Loss: 1.1760, Val Accuracy: 0.7366 Epoch 9463/10000, Train Loss: 1.0263, Train Accuracy: 0.8828, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9464/10000, Train Loss: 1.0313, Train Accuracy: 0.8750, Val Loss: 1.1759, Val Accuracy: 0.7366 Epoch 9465/10000, Train Loss: 1.0380, Train Accuracy: 0.8783, Val Loss: 1.1759, Val Accuracy: 0.7411 Epoch 9466/10000, Train Loss: 1.0332, Train Accuracy: 0.8817, Val Loss: 1.1756, Val Accuracy: 0.7411 Epoch 9467/10000, Train Loss: 1.0390, Train Accuracy: 0.8638, Val Loss: 1.1756, Val Accuracy: 0.7411 Epoch 9468/10000, Train Loss: 1.0287, Train Accuracy: 0.8817, Val Loss: 1.1757, Val Accuracy: 0.7411 Epoch 9469/10000, Train Loss: 1.0358, Train Accuracy: 0.8761, Val Loss: 1.1756, Val Accuracy: 0.7411 Epoch 9470/10000, Train Loss: 1.0376, Train Accuracy: 0.8717, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 9471/10000, Train Loss: 1.0325, Train Accuracy: 0.8795, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 9472/10000, Train Loss: 1.0337, Train Accuracy: 0.8761, Val Loss: 1.1750, Val Accuracy: 0.7411 Epoch 9473/10000, Train Loss: 1.0305, Train Accuracy: 0.8761, Val Loss: 1.1749, Val Accuracy: 0.7411 Epoch 9474/10000, Train Loss: 1.0399, Train Accuracy: 0.8672, Val Loss: 1.1749, Val Accuracy: 0.7411 Epoch 9475/10000, Train Loss: 1.0319, Train Accuracy: 0.8795, Val Loss: 1.1750, Val Accuracy: 0.7411 Epoch 9476/10000, Train Loss: 1.0278, Train Accuracy: 0.8884, Val Loss: 1.1751, Val Accuracy: 0.7411 Epoch 9477/10000, Train Loss: 1.0244, Train Accuracy: 0.8929, Val Loss: 1.1752, Val Accuracy: 0.7411 Epoch 9478/10000, Train Loss: 1.0360, Train Accuracy: 0.8772, Val Loss: 1.1753, Val Accuracy: 0.7411 Epoch 9479/10000, Train Loss: 1.0337, Train Accuracy: 0.8783, Val Loss: 1.1755, Val Accuracy: 0.7411 Epoch 9480/10000, Train Loss: 1.0373, Train Accuracy: 0.8783, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 9481/10000, Train Loss: 1.0206, Train Accuracy: 0.8996, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 9482/10000, Train Loss: 1.0399, Train Accuracy: 0.8750, Val Loss: 1.1752, Val Accuracy: 0.7411 Epoch 9483/10000, Train Loss: 1.0262, Train Accuracy: 0.8884, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9484/10000, Train Loss: 1.0279, Train Accuracy: 0.8783, Val Loss: 1.1754, Val Accuracy: 0.7411 Epoch 9485/10000, Train Loss: 1.0337, Train Accuracy: 0.8772, Val Loss: 1.1752, Val Accuracy: 0.7411 Epoch 9486/10000, Train Loss: 1.0268, Train Accuracy: 0.8884, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9487/10000, Train Loss: 1.0328, Train Accuracy: 0.8772, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9488/10000, Train Loss: 1.0395, Train Accuracy: 0.8683, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9489/10000, Train Loss: 1.0367, Train Accuracy: 0.8750, Val Loss: 1.1753, Val Accuracy: 0.7366 Epoch 9490/10000, Train Loss: 1.0222, Train Accuracy: 0.8940, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9491/10000, Train Loss: 1.0273, Train Accuracy: 0.8873, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9492/10000, Train Loss: 1.0204, Train Accuracy: 0.8906, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9493/10000, Train Loss: 1.0292, Train Accuracy: 0.8862, Val Loss: 1.1754, Val Accuracy: 0.7366 Epoch 9494/10000, Train Loss: 1.0282, Train Accuracy: 0.8884, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9495/10000, Train Loss: 1.0381, Train Accuracy: 0.8795, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9496/10000, Train Loss: 1.0342, Train Accuracy: 0.8772, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9497/10000, Train Loss: 1.0263, Train Accuracy: 0.8839, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9498/10000, Train Loss: 1.0360, Train Accuracy: 0.8783, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9499/10000, Train Loss: 1.0341, Train Accuracy: 0.8728, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9500/10000, Train Loss: 1.0247, Train Accuracy: 0.8906, Val Loss: 1.1750, Val Accuracy: 0.7366 Epoch 9501/10000, Train Loss: 1.0244, Train Accuracy: 0.8884, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9502/10000, Train Loss: 1.0429, Train Accuracy: 0.8672, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9503/10000, Train Loss: 1.0429, Train Accuracy: 0.8616, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9504/10000, Train Loss: 1.0242, Train Accuracy: 0.8895, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9505/10000, Train Loss: 1.0309, Train Accuracy: 0.8806, Val Loss: 1.1751, Val Accuracy: 0.7366 Epoch 9506/10000, Train Loss: 1.0261, Train Accuracy: 0.8839, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9507/10000, Train Loss: 1.0166, Train Accuracy: 0.8929, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9508/10000, Train Loss: 1.0295, Train Accuracy: 0.8839, Val Loss: 1.1756, Val Accuracy: 0.7277 Epoch 9509/10000, Train Loss: 1.0413, Train Accuracy: 0.8705, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9510/10000, Train Loss: 1.0260, Train Accuracy: 0.8828, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9511/10000, Train Loss: 1.0380, Train Accuracy: 0.8728, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9512/10000, Train Loss: 1.0246, Train Accuracy: 0.8850, Val Loss: 1.1759, Val Accuracy: 0.7277 Epoch 9513/10000, Train Loss: 1.0226, Train Accuracy: 0.8895, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 9514/10000, Train Loss: 1.0306, Train Accuracy: 0.8795, Val Loss: 1.1756, Val Accuracy: 0.7277 Epoch 9515/10000, Train Loss: 1.0302, Train Accuracy: 0.8850, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9516/10000, Train Loss: 1.0286, Train Accuracy: 0.8850, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9517/10000, Train Loss: 1.0340, Train Accuracy: 0.8728, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9518/10000, Train Loss: 1.0225, Train Accuracy: 0.8951, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9519/10000, Train Loss: 1.0265, Train Accuracy: 0.8873, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 9520/10000, Train Loss: 1.0332, Train Accuracy: 0.8817, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9521/10000, Train Loss: 1.0353, Train Accuracy: 0.8795, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9522/10000, Train Loss: 1.0224, Train Accuracy: 0.8951, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9523/10000, Train Loss: 1.0371, Train Accuracy: 0.8728, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9524/10000, Train Loss: 1.0217, Train Accuracy: 0.8884, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9525/10000, Train Loss: 1.0270, Train Accuracy: 0.8795, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9526/10000, Train Loss: 1.0244, Train Accuracy: 0.8895, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9527/10000, Train Loss: 1.0319, Train Accuracy: 0.8739, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9528/10000, Train Loss: 1.0255, Train Accuracy: 0.8828, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9529/10000, Train Loss: 1.0334, Train Accuracy: 0.8750, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9530/10000, Train Loss: 1.0240, Train Accuracy: 0.8884, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9531/10000, Train Loss: 1.0362, Train Accuracy: 0.8772, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9532/10000, Train Loss: 1.0407, Train Accuracy: 0.8672, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9533/10000, Train Loss: 1.0286, Train Accuracy: 0.8750, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9534/10000, Train Loss: 1.0332, Train Accuracy: 0.8761, Val Loss: 1.1758, Val Accuracy: 0.7277 Epoch 9535/10000, Train Loss: 1.0236, Train Accuracy: 0.8884, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9536/10000, Train Loss: 1.0265, Train Accuracy: 0.8839, Val Loss: 1.1757, Val Accuracy: 0.7277 Epoch 9537/10000, Train Loss: 1.0304, Train Accuracy: 0.8862, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9538/10000, Train Loss: 1.0353, Train Accuracy: 0.8728, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9539/10000, Train Loss: 1.0378, Train Accuracy: 0.8728, Val Loss: 1.1761, Val Accuracy: 0.7232 Epoch 9540/10000, Train Loss: 1.0293, Train Accuracy: 0.8862, Val Loss: 1.1762, Val Accuracy: 0.7188 Epoch 9541/10000, Train Loss: 1.0179, Train Accuracy: 0.8962, Val Loss: 1.1760, Val Accuracy: 0.7188 Epoch 9542/10000, Train Loss: 1.0474, Train Accuracy: 0.8594, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9543/10000, Train Loss: 1.0325, Train Accuracy: 0.8750, Val Loss: 1.1755, Val Accuracy: 0.7232 Epoch 9544/10000, Train Loss: 1.0335, Train Accuracy: 0.8761, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9545/10000, Train Loss: 1.0273, Train Accuracy: 0.8817, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9546/10000, Train Loss: 1.0203, Train Accuracy: 0.8940, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9547/10000, Train Loss: 1.0318, Train Accuracy: 0.8862, Val Loss: 1.1750, Val Accuracy: 0.7232 Epoch 9548/10000, Train Loss: 1.0193, Train Accuracy: 0.8996, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9549/10000, Train Loss: 1.0305, Train Accuracy: 0.8862, Val Loss: 1.1752, Val Accuracy: 0.7277 Epoch 9550/10000, Train Loss: 1.0402, Train Accuracy: 0.8761, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9551/10000, Train Loss: 1.0488, Train Accuracy: 0.8594, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9552/10000, Train Loss: 1.0332, Train Accuracy: 0.8817, Val Loss: 1.1752, Val Accuracy: 0.7232 Epoch 9553/10000, Train Loss: 1.0335, Train Accuracy: 0.8783, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9554/10000, Train Loss: 1.0322, Train Accuracy: 0.8761, Val Loss: 1.1754, Val Accuracy: 0.7232 Epoch 9555/10000, Train Loss: 1.0232, Train Accuracy: 0.8850, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9556/10000, Train Loss: 1.0305, Train Accuracy: 0.8839, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9557/10000, Train Loss: 1.0275, Train Accuracy: 0.8850, Val Loss: 1.1751, Val Accuracy: 0.7321 Epoch 9558/10000, Train Loss: 1.0245, Train Accuracy: 0.8850, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9559/10000, Train Loss: 1.0211, Train Accuracy: 0.8951, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9560/10000, Train Loss: 1.0354, Train Accuracy: 0.8828, Val Loss: 1.1752, Val Accuracy: 0.7277 Epoch 9561/10000, Train Loss: 1.0267, Train Accuracy: 0.8862, Val Loss: 1.1752, Val Accuracy: 0.7277 Epoch 9562/10000, Train Loss: 1.0228, Train Accuracy: 0.8862, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9563/10000, Train Loss: 1.0251, Train Accuracy: 0.8806, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9564/10000, Train Loss: 1.0316, Train Accuracy: 0.8839, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9565/10000, Train Loss: 1.0265, Train Accuracy: 0.8850, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9566/10000, Train Loss: 1.0258, Train Accuracy: 0.8828, Val Loss: 1.1747, Val Accuracy: 0.7277 Epoch 9567/10000, Train Loss: 1.0273, Train Accuracy: 0.8884, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9568/10000, Train Loss: 1.0287, Train Accuracy: 0.8806, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9569/10000, Train Loss: 1.0341, Train Accuracy: 0.8761, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9570/10000, Train Loss: 1.0312, Train Accuracy: 0.8828, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9571/10000, Train Loss: 1.0371, Train Accuracy: 0.8717, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9572/10000, Train Loss: 1.0418, Train Accuracy: 0.8672, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9573/10000, Train Loss: 1.0291, Train Accuracy: 0.8828, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9574/10000, Train Loss: 1.0266, Train Accuracy: 0.8862, Val Loss: 1.1737, Val Accuracy: 0.7321 Epoch 9575/10000, Train Loss: 1.0268, Train Accuracy: 0.8862, Val Loss: 1.1736, Val Accuracy: 0.7321 Epoch 9576/10000, Train Loss: 1.0310, Train Accuracy: 0.8795, Val Loss: 1.1734, Val Accuracy: 0.7321 Epoch 9577/10000, Train Loss: 1.0192, Train Accuracy: 0.8895, Val Loss: 1.1735, Val Accuracy: 0.7321 Epoch 9578/10000, Train Loss: 1.0291, Train Accuracy: 0.8795, Val Loss: 1.1734, Val Accuracy: 0.7321 Epoch 9579/10000, Train Loss: 1.0491, Train Accuracy: 0.8638, Val Loss: 1.1736, Val Accuracy: 0.7321 Epoch 9580/10000, Train Loss: 1.0331, Train Accuracy: 0.8750, Val Loss: 1.1733, Val Accuracy: 0.7321 Epoch 9581/10000, Train Loss: 1.0287, Train Accuracy: 0.8817, Val Loss: 1.1735, Val Accuracy: 0.7321 Epoch 9582/10000, Train Loss: 1.0273, Train Accuracy: 0.8862, Val Loss: 1.1736, Val Accuracy: 0.7321 Epoch 9583/10000, Train Loss: 1.0271, Train Accuracy: 0.8783, Val Loss: 1.1737, Val Accuracy: 0.7321 Epoch 9584/10000, Train Loss: 1.0309, Train Accuracy: 0.8795, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9585/10000, Train Loss: 1.0346, Train Accuracy: 0.8828, Val Loss: 1.1737, Val Accuracy: 0.7321 Epoch 9586/10000, Train Loss: 1.0339, Train Accuracy: 0.8772, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9587/10000, Train Loss: 1.0150, Train Accuracy: 0.8996, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9588/10000, Train Loss: 1.0266, Train Accuracy: 0.8862, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9589/10000, Train Loss: 1.0258, Train Accuracy: 0.8839, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9590/10000, Train Loss: 1.0236, Train Accuracy: 0.8906, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9591/10000, Train Loss: 1.0363, Train Accuracy: 0.8728, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9592/10000, Train Loss: 1.0219, Train Accuracy: 0.8962, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9593/10000, Train Loss: 1.0316, Train Accuracy: 0.8795, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9594/10000, Train Loss: 1.0172, Train Accuracy: 0.8984, Val Loss: 1.1745, Val Accuracy: 0.7277 Epoch 9595/10000, Train Loss: 1.0275, Train Accuracy: 0.8862, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9596/10000, Train Loss: 1.0210, Train Accuracy: 0.8873, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9597/10000, Train Loss: 1.0258, Train Accuracy: 0.8862, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9598/10000, Train Loss: 1.0251, Train Accuracy: 0.8839, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9599/10000, Train Loss: 1.0387, Train Accuracy: 0.8683, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9600/10000, Train Loss: 1.0259, Train Accuracy: 0.8828, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9601/10000, Train Loss: 1.0456, Train Accuracy: 0.8616, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9602/10000, Train Loss: 1.0316, Train Accuracy: 0.8750, Val Loss: 1.1737, Val Accuracy: 0.7321 Epoch 9603/10000, Train Loss: 1.0392, Train Accuracy: 0.8717, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9604/10000, Train Loss: 1.0211, Train Accuracy: 0.8917, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9605/10000, Train Loss: 1.0257, Train Accuracy: 0.8873, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9606/10000, Train Loss: 1.0286, Train Accuracy: 0.8828, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9607/10000, Train Loss: 1.0315, Train Accuracy: 0.8862, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9608/10000, Train Loss: 1.0253, Train Accuracy: 0.8917, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9609/10000, Train Loss: 1.0350, Train Accuracy: 0.8761, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9610/10000, Train Loss: 1.0238, Train Accuracy: 0.8895, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9611/10000, Train Loss: 1.0289, Train Accuracy: 0.8862, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9612/10000, Train Loss: 1.0263, Train Accuracy: 0.8828, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9613/10000, Train Loss: 1.0281, Train Accuracy: 0.8850, Val Loss: 1.1737, Val Accuracy: 0.7321 Epoch 9614/10000, Train Loss: 1.0268, Train Accuracy: 0.8850, Val Loss: 1.1734, Val Accuracy: 0.7366 Epoch 9615/10000, Train Loss: 1.0299, Train Accuracy: 0.8862, Val Loss: 1.1734, Val Accuracy: 0.7321 Epoch 9616/10000, Train Loss: 1.0325, Train Accuracy: 0.8795, Val Loss: 1.1738, Val Accuracy: 0.7321 Epoch 9617/10000, Train Loss: 1.0339, Train Accuracy: 0.8728, Val Loss: 1.1737, Val Accuracy: 0.7321 Epoch 9618/10000, Train Loss: 1.0359, Train Accuracy: 0.8795, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9619/10000, Train Loss: 1.0228, Train Accuracy: 0.8873, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9620/10000, Train Loss: 1.0306, Train Accuracy: 0.8884, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9621/10000, Train Loss: 1.0290, Train Accuracy: 0.8772, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9622/10000, Train Loss: 1.0267, Train Accuracy: 0.8906, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9623/10000, Train Loss: 1.0360, Train Accuracy: 0.8717, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9624/10000, Train Loss: 1.0296, Train Accuracy: 0.8795, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9625/10000, Train Loss: 1.0220, Train Accuracy: 0.8884, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9626/10000, Train Loss: 1.0252, Train Accuracy: 0.8873, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9627/10000, Train Loss: 1.0347, Train Accuracy: 0.8705, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9628/10000, Train Loss: 1.0166, Train Accuracy: 0.8973, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9629/10000, Train Loss: 1.0219, Train Accuracy: 0.8884, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9630/10000, Train Loss: 1.0261, Train Accuracy: 0.8873, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9631/10000, Train Loss: 1.0273, Train Accuracy: 0.8839, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9632/10000, Train Loss: 1.0261, Train Accuracy: 0.8817, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9633/10000, Train Loss: 1.0185, Train Accuracy: 0.8895, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9634/10000, Train Loss: 1.0251, Train Accuracy: 0.8873, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9635/10000, Train Loss: 1.0292, Train Accuracy: 0.8828, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9636/10000, Train Loss: 1.0217, Train Accuracy: 0.8884, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9637/10000, Train Loss: 1.0281, Train Accuracy: 0.8862, Val Loss: 1.1739, Val Accuracy: 0.7277 Epoch 9638/10000, Train Loss: 1.0466, Train Accuracy: 0.8560, Val Loss: 1.1735, Val Accuracy: 0.7277 Epoch 9639/10000, Train Loss: 1.0217, Train Accuracy: 0.8917, Val Loss: 1.1738, Val Accuracy: 0.7277 Epoch 9640/10000, Train Loss: 1.0361, Train Accuracy: 0.8783, Val Loss: 1.1739, Val Accuracy: 0.7277 Epoch 9641/10000, Train Loss: 1.0306, Train Accuracy: 0.8783, Val Loss: 1.1741, Val Accuracy: 0.7277 Epoch 9642/10000, Train Loss: 1.0226, Train Accuracy: 0.8940, Val Loss: 1.1740, Val Accuracy: 0.7277 Epoch 9643/10000, Train Loss: 1.0199, Train Accuracy: 0.8906, Val Loss: 1.1741, Val Accuracy: 0.7277 Epoch 9644/10000, Train Loss: 1.0329, Train Accuracy: 0.8750, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9645/10000, Train Loss: 1.0283, Train Accuracy: 0.8828, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9646/10000, Train Loss: 1.0295, Train Accuracy: 0.8839, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9647/10000, Train Loss: 1.0257, Train Accuracy: 0.8850, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9648/10000, Train Loss: 1.0293, Train Accuracy: 0.8862, Val Loss: 1.1747, Val Accuracy: 0.7277 Epoch 9649/10000, Train Loss: 1.0274, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9650/10000, Train Loss: 1.0265, Train Accuracy: 0.8828, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9651/10000, Train Loss: 1.0335, Train Accuracy: 0.8783, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9652/10000, Train Loss: 1.0294, Train Accuracy: 0.8806, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9653/10000, Train Loss: 1.0218, Train Accuracy: 0.8895, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9654/10000, Train Loss: 1.0369, Train Accuracy: 0.8783, Val Loss: 1.1741, Val Accuracy: 0.7277 Epoch 9655/10000, Train Loss: 1.0148, Train Accuracy: 0.8973, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9656/10000, Train Loss: 1.0244, Train Accuracy: 0.8850, Val Loss: 1.1745, Val Accuracy: 0.7277 Epoch 9657/10000, Train Loss: 1.0322, Train Accuracy: 0.8750, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9658/10000, Train Loss: 1.0237, Train Accuracy: 0.8873, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9659/10000, Train Loss: 1.0345, Train Accuracy: 0.8772, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9660/10000, Train Loss: 1.0341, Train Accuracy: 0.8761, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9661/10000, Train Loss: 1.0269, Train Accuracy: 0.8850, Val Loss: 1.1746, Val Accuracy: 0.7321 Epoch 9662/10000, Train Loss: 1.0395, Train Accuracy: 0.8728, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9663/10000, Train Loss: 1.0320, Train Accuracy: 0.8783, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9664/10000, Train Loss: 1.0216, Train Accuracy: 0.8917, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9665/10000, Train Loss: 1.0291, Train Accuracy: 0.8806, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9666/10000, Train Loss: 1.0232, Train Accuracy: 0.8862, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9667/10000, Train Loss: 1.0250, Train Accuracy: 0.8929, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9668/10000, Train Loss: 1.0309, Train Accuracy: 0.8817, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9669/10000, Train Loss: 1.0274, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9670/10000, Train Loss: 1.0271, Train Accuracy: 0.8806, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9671/10000, Train Loss: 1.0336, Train Accuracy: 0.8783, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9672/10000, Train Loss: 1.0378, Train Accuracy: 0.8728, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9673/10000, Train Loss: 1.0197, Train Accuracy: 0.8962, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9674/10000, Train Loss: 1.0245, Train Accuracy: 0.8873, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9675/10000, Train Loss: 1.0321, Train Accuracy: 0.8750, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9676/10000, Train Loss: 1.0319, Train Accuracy: 0.8817, Val Loss: 1.1747, Val Accuracy: 0.7366 Epoch 9677/10000, Train Loss: 1.0268, Train Accuracy: 0.8884, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9678/10000, Train Loss: 1.0242, Train Accuracy: 0.8795, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9679/10000, Train Loss: 1.0274, Train Accuracy: 0.8884, Val Loss: 1.1754, Val Accuracy: 0.7232 Epoch 9680/10000, Train Loss: 1.0357, Train Accuracy: 0.8772, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9681/10000, Train Loss: 1.0293, Train Accuracy: 0.8817, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9682/10000, Train Loss: 1.0138, Train Accuracy: 0.8940, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9683/10000, Train Loss: 1.0252, Train Accuracy: 0.8817, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9684/10000, Train Loss: 1.0265, Train Accuracy: 0.8862, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9685/10000, Train Loss: 1.0266, Train Accuracy: 0.8828, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9686/10000, Train Loss: 1.0282, Train Accuracy: 0.8795, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9687/10000, Train Loss: 1.0216, Train Accuracy: 0.8906, Val Loss: 1.1752, Val Accuracy: 0.7277 Epoch 9688/10000, Train Loss: 1.0478, Train Accuracy: 0.8638, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9689/10000, Train Loss: 1.0190, Train Accuracy: 0.8984, Val Loss: 1.1754, Val Accuracy: 0.7232 Epoch 9690/10000, Train Loss: 1.0313, Train Accuracy: 0.8783, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9691/10000, Train Loss: 1.0236, Train Accuracy: 0.8929, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9692/10000, Train Loss: 1.0300, Train Accuracy: 0.8772, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9693/10000, Train Loss: 1.0259, Train Accuracy: 0.8850, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9694/10000, Train Loss: 1.0182, Train Accuracy: 0.8973, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9695/10000, Train Loss: 1.0236, Train Accuracy: 0.8951, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9696/10000, Train Loss: 1.0176, Train Accuracy: 0.8940, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9697/10000, Train Loss: 1.0185, Train Accuracy: 0.8940, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9698/10000, Train Loss: 1.0294, Train Accuracy: 0.8817, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9699/10000, Train Loss: 1.0394, Train Accuracy: 0.8683, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9700/10000, Train Loss: 1.0247, Train Accuracy: 0.8850, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9701/10000, Train Loss: 1.0391, Train Accuracy: 0.8705, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9702/10000, Train Loss: 1.0393, Train Accuracy: 0.8683, Val Loss: 1.1755, Val Accuracy: 0.7232 Epoch 9703/10000, Train Loss: 1.0214, Train Accuracy: 0.8929, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9704/10000, Train Loss: 1.0235, Train Accuracy: 0.8940, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9705/10000, Train Loss: 1.0212, Train Accuracy: 0.8884, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9706/10000, Train Loss: 1.0248, Train Accuracy: 0.8850, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9707/10000, Train Loss: 1.0404, Train Accuracy: 0.8661, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9708/10000, Train Loss: 1.0233, Train Accuracy: 0.8884, Val Loss: 1.1747, Val Accuracy: 0.7277 Epoch 9709/10000, Train Loss: 1.0251, Train Accuracy: 0.8828, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9710/10000, Train Loss: 1.0347, Train Accuracy: 0.8817, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9711/10000, Train Loss: 1.0168, Train Accuracy: 0.9018, Val Loss: 1.1745, Val Accuracy: 0.7277 Epoch 9712/10000, Train Loss: 1.0230, Train Accuracy: 0.8862, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9713/10000, Train Loss: 1.0398, Train Accuracy: 0.8717, Val Loss: 1.1747, Val Accuracy: 0.7277 Epoch 9714/10000, Train Loss: 1.0226, Train Accuracy: 0.8884, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9715/10000, Train Loss: 1.0347, Train Accuracy: 0.8806, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9716/10000, Train Loss: 1.0314, Train Accuracy: 0.8772, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9717/10000, Train Loss: 1.0209, Train Accuracy: 0.8940, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9718/10000, Train Loss: 1.0290, Train Accuracy: 0.8839, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9719/10000, Train Loss: 1.0399, Train Accuracy: 0.8661, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9720/10000, Train Loss: 1.0177, Train Accuracy: 0.8951, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9721/10000, Train Loss: 1.0228, Train Accuracy: 0.8862, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9722/10000, Train Loss: 1.0169, Train Accuracy: 0.8906, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9723/10000, Train Loss: 1.0435, Train Accuracy: 0.8616, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9724/10000, Train Loss: 1.0201, Train Accuracy: 0.8951, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9725/10000, Train Loss: 1.0189, Train Accuracy: 0.8906, Val Loss: 1.1749, Val Accuracy: 0.7366 Epoch 9726/10000, Train Loss: 1.0312, Train Accuracy: 0.8772, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9727/10000, Train Loss: 1.0412, Train Accuracy: 0.8705, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9728/10000, Train Loss: 1.0277, Train Accuracy: 0.8795, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9729/10000, Train Loss: 1.0223, Train Accuracy: 0.8917, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9730/10000, Train Loss: 1.0279, Train Accuracy: 0.8817, Val Loss: 1.1744, Val Accuracy: 0.7366 Epoch 9731/10000, Train Loss: 1.0299, Train Accuracy: 0.8817, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9732/10000, Train Loss: 1.0335, Train Accuracy: 0.8772, Val Loss: 1.1742, Val Accuracy: 0.7366 Epoch 9733/10000, Train Loss: 1.0219, Train Accuracy: 0.8951, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9734/10000, Train Loss: 1.0263, Train Accuracy: 0.8873, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9735/10000, Train Loss: 1.0228, Train Accuracy: 0.8984, Val Loss: 1.1744, Val Accuracy: 0.7277 Epoch 9736/10000, Train Loss: 1.0321, Train Accuracy: 0.8795, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9737/10000, Train Loss: 1.0233, Train Accuracy: 0.8873, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9738/10000, Train Loss: 1.0283, Train Accuracy: 0.8839, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9739/10000, Train Loss: 1.0319, Train Accuracy: 0.8850, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9740/10000, Train Loss: 1.0283, Train Accuracy: 0.8817, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9741/10000, Train Loss: 1.0145, Train Accuracy: 0.9029, Val Loss: 1.1745, Val Accuracy: 0.7321 Epoch 9742/10000, Train Loss: 1.0363, Train Accuracy: 0.8750, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9743/10000, Train Loss: 1.0410, Train Accuracy: 0.8705, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9744/10000, Train Loss: 1.0257, Train Accuracy: 0.8862, Val Loss: 1.1744, Val Accuracy: 0.7321 Epoch 9745/10000, Train Loss: 1.0306, Train Accuracy: 0.8772, Val Loss: 1.1748, Val Accuracy: 0.7321 Epoch 9746/10000, Train Loss: 1.0284, Train Accuracy: 0.8862, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9747/10000, Train Loss: 1.0217, Train Accuracy: 0.8929, Val Loss: 1.1748, Val Accuracy: 0.7366 Epoch 9748/10000, Train Loss: 1.0312, Train Accuracy: 0.8839, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9749/10000, Train Loss: 1.0293, Train Accuracy: 0.8795, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9750/10000, Train Loss: 1.0341, Train Accuracy: 0.8795, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9751/10000, Train Loss: 1.0262, Train Accuracy: 0.8839, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9752/10000, Train Loss: 1.0275, Train Accuracy: 0.8806, Val Loss: 1.1756, Val Accuracy: 0.7277 Epoch 9753/10000, Train Loss: 1.0142, Train Accuracy: 0.8962, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9754/10000, Train Loss: 1.0278, Train Accuracy: 0.8839, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9755/10000, Train Loss: 1.0325, Train Accuracy: 0.8772, Val Loss: 1.1756, Val Accuracy: 0.7277 Epoch 9756/10000, Train Loss: 1.0217, Train Accuracy: 0.8951, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9757/10000, Train Loss: 1.0367, Train Accuracy: 0.8683, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9758/10000, Train Loss: 1.0337, Train Accuracy: 0.8717, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9759/10000, Train Loss: 1.0346, Train Accuracy: 0.8772, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9760/10000, Train Loss: 1.0333, Train Accuracy: 0.8783, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9761/10000, Train Loss: 1.0270, Train Accuracy: 0.8873, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9762/10000, Train Loss: 1.0206, Train Accuracy: 0.8929, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9763/10000, Train Loss: 1.0360, Train Accuracy: 0.8772, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9764/10000, Train Loss: 1.0212, Train Accuracy: 0.8951, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9765/10000, Train Loss: 1.0334, Train Accuracy: 0.8783, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9766/10000, Train Loss: 1.0236, Train Accuracy: 0.8862, Val Loss: 1.1759, Val Accuracy: 0.7188 Epoch 9767/10000, Train Loss: 1.0205, Train Accuracy: 0.8962, Val Loss: 1.1761, Val Accuracy: 0.7188 Epoch 9768/10000, Train Loss: 1.0242, Train Accuracy: 0.8806, Val Loss: 1.1761, Val Accuracy: 0.7188 Epoch 9769/10000, Train Loss: 1.0256, Train Accuracy: 0.8839, Val Loss: 1.1759, Val Accuracy: 0.7188 Epoch 9770/10000, Train Loss: 1.0123, Train Accuracy: 0.8996, Val Loss: 1.1763, Val Accuracy: 0.7188 Epoch 9771/10000, Train Loss: 1.0347, Train Accuracy: 0.8739, Val Loss: 1.1764, Val Accuracy: 0.7188 Epoch 9772/10000, Train Loss: 1.0334, Train Accuracy: 0.8761, Val Loss: 1.1762, Val Accuracy: 0.7188 Epoch 9773/10000, Train Loss: 1.0170, Train Accuracy: 0.9018, Val Loss: 1.1762, Val Accuracy: 0.7188 Epoch 9774/10000, Train Loss: 1.0254, Train Accuracy: 0.8839, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9775/10000, Train Loss: 1.0385, Train Accuracy: 0.8772, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9776/10000, Train Loss: 1.0292, Train Accuracy: 0.8761, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9777/10000, Train Loss: 1.0350, Train Accuracy: 0.8761, Val Loss: 1.1756, Val Accuracy: 0.7188 Epoch 9778/10000, Train Loss: 1.0240, Train Accuracy: 0.8817, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9779/10000, Train Loss: 1.0192, Train Accuracy: 0.8962, Val Loss: 1.1756, Val Accuracy: 0.7232 Epoch 9780/10000, Train Loss: 1.0287, Train Accuracy: 0.8873, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9781/10000, Train Loss: 1.0164, Train Accuracy: 0.8951, Val Loss: 1.1756, Val Accuracy: 0.7321 Epoch 9782/10000, Train Loss: 1.0177, Train Accuracy: 0.8940, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9783/10000, Train Loss: 1.0356, Train Accuracy: 0.8717, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9784/10000, Train Loss: 1.0231, Train Accuracy: 0.8806, Val Loss: 1.1757, Val Accuracy: 0.7321 Epoch 9785/10000, Train Loss: 1.0172, Train Accuracy: 0.8951, Val Loss: 1.1759, Val Accuracy: 0.7321 Epoch 9786/10000, Train Loss: 1.0227, Train Accuracy: 0.8839, Val Loss: 1.1755, Val Accuracy: 0.7321 Epoch 9787/10000, Train Loss: 1.0177, Train Accuracy: 0.8884, Val Loss: 1.1753, Val Accuracy: 0.7321 Epoch 9788/10000, Train Loss: 1.0158, Train Accuracy: 0.9051, Val Loss: 1.1754, Val Accuracy: 0.7321 Epoch 9789/10000, Train Loss: 1.0334, Train Accuracy: 0.8783, Val Loss: 1.1750, Val Accuracy: 0.7321 Epoch 9790/10000, Train Loss: 1.0204, Train Accuracy: 0.8862, Val Loss: 1.1749, Val Accuracy: 0.7321 Epoch 9791/10000, Train Loss: 1.0217, Train Accuracy: 0.8884, Val Loss: 1.1752, Val Accuracy: 0.7321 Epoch 9792/10000, Train Loss: 1.0259, Train Accuracy: 0.8884, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9793/10000, Train Loss: 1.0236, Train Accuracy: 0.8850, Val Loss: 1.1758, Val Accuracy: 0.7232 Epoch 9794/10000, Train Loss: 1.0303, Train Accuracy: 0.8795, Val Loss: 1.1758, Val Accuracy: 0.7188 Epoch 9795/10000, Train Loss: 1.0260, Train Accuracy: 0.8862, Val Loss: 1.1757, Val Accuracy: 0.7188 Epoch 9796/10000, Train Loss: 1.0251, Train Accuracy: 0.8873, Val Loss: 1.1755, Val Accuracy: 0.7277 Epoch 9797/10000, Train Loss: 1.0316, Train Accuracy: 0.8783, Val Loss: 1.1757, Val Accuracy: 0.7188 Epoch 9798/10000, Train Loss: 1.0178, Train Accuracy: 0.8917, Val Loss: 1.1760, Val Accuracy: 0.7188 Epoch 9799/10000, Train Loss: 1.0222, Train Accuracy: 0.8884, Val Loss: 1.1760, Val Accuracy: 0.7232 Epoch 9800/10000, Train Loss: 1.0253, Train Accuracy: 0.8917, Val Loss: 1.1760, Val Accuracy: 0.7188 Epoch 9801/10000, Train Loss: 1.0331, Train Accuracy: 0.8817, Val Loss: 1.1759, Val Accuracy: 0.7232 Epoch 9802/10000, Train Loss: 1.0250, Train Accuracy: 0.8862, Val Loss: 1.1757, Val Accuracy: 0.7232 Epoch 9803/10000, Train Loss: 1.0306, Train Accuracy: 0.8828, Val Loss: 1.1757, Val Accuracy: 0.7188 Epoch 9804/10000, Train Loss: 1.0258, Train Accuracy: 0.8839, Val Loss: 1.1757, Val Accuracy: 0.7188 Epoch 9805/10000, Train Loss: 1.0244, Train Accuracy: 0.8884, Val Loss: 1.1758, Val Accuracy: 0.7188 Epoch 9806/10000, Train Loss: 1.0292, Train Accuracy: 0.8817, Val Loss: 1.1759, Val Accuracy: 0.7188 Epoch 9807/10000, Train Loss: 1.0287, Train Accuracy: 0.8806, Val Loss: 1.1757, Val Accuracy: 0.7188 Epoch 9808/10000, Train Loss: 1.0229, Train Accuracy: 0.8906, Val Loss: 1.1755, Val Accuracy: 0.7188 Epoch 9809/10000, Train Loss: 1.0244, Train Accuracy: 0.8828, Val Loss: 1.1755, Val Accuracy: 0.7188 Epoch 9810/10000, Train Loss: 1.0213, Train Accuracy: 0.8884, Val Loss: 1.1753, Val Accuracy: 0.7232 Epoch 9811/10000, Train Loss: 1.0236, Train Accuracy: 0.8873, Val Loss: 1.1754, Val Accuracy: 0.7188 Epoch 9812/10000, Train Loss: 1.0323, Train Accuracy: 0.8672, Val Loss: 1.1756, Val Accuracy: 0.7188 Epoch 9813/10000, Train Loss: 1.0188, Train Accuracy: 0.8929, Val Loss: 1.1757, Val Accuracy: 0.7188 Epoch 9814/10000, Train Loss: 1.0310, Train Accuracy: 0.8783, Val Loss: 1.1755, Val Accuracy: 0.7232 Epoch 9815/10000, Train Loss: 1.0178, Train Accuracy: 0.8917, Val Loss: 1.1755, Val Accuracy: 0.7188 Epoch 9816/10000, Train Loss: 1.0191, Train Accuracy: 0.8929, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9817/10000, Train Loss: 1.0269, Train Accuracy: 0.8850, Val Loss: 1.1754, Val Accuracy: 0.7188 Epoch 9818/10000, Train Loss: 1.0220, Train Accuracy: 0.8951, Val Loss: 1.1752, Val Accuracy: 0.7277 Epoch 9819/10000, Train Loss: 1.0290, Train Accuracy: 0.8828, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9820/10000, Train Loss: 1.0245, Train Accuracy: 0.8895, Val Loss: 1.1753, Val Accuracy: 0.7232 Epoch 9821/10000, Train Loss: 1.0148, Train Accuracy: 0.8951, Val Loss: 1.1753, Val Accuracy: 0.7232 Epoch 9822/10000, Train Loss: 1.0244, Train Accuracy: 0.8828, Val Loss: 1.1754, Val Accuracy: 0.7277 Epoch 9823/10000, Train Loss: 1.0256, Train Accuracy: 0.8850, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9824/10000, Train Loss: 1.0321, Train Accuracy: 0.8750, Val Loss: 1.1751, Val Accuracy: 0.7277 Epoch 9825/10000, Train Loss: 1.0274, Train Accuracy: 0.8828, Val Loss: 1.1751, Val Accuracy: 0.7232 Epoch 9826/10000, Train Loss: 1.0260, Train Accuracy: 0.8906, Val Loss: 1.1753, Val Accuracy: 0.7143 Epoch 9827/10000, Train Loss: 1.0266, Train Accuracy: 0.8839, Val Loss: 1.1753, Val Accuracy: 0.7188 Epoch 9828/10000, Train Loss: 1.0162, Train Accuracy: 0.9007, Val Loss: 1.1757, Val Accuracy: 0.7143 Epoch 9829/10000, Train Loss: 1.0205, Train Accuracy: 0.8873, Val Loss: 1.1755, Val Accuracy: 0.7232 Epoch 9830/10000, Train Loss: 1.0203, Train Accuracy: 0.8884, Val Loss: 1.1757, Val Accuracy: 0.7143 Epoch 9831/10000, Train Loss: 1.0231, Train Accuracy: 0.8895, Val Loss: 1.1754, Val Accuracy: 0.7143 Epoch 9832/10000, Train Loss: 1.0308, Train Accuracy: 0.8806, Val Loss: 1.1753, Val Accuracy: 0.7143 Epoch 9833/10000, Train Loss: 1.0316, Train Accuracy: 0.8772, Val Loss: 1.1755, Val Accuracy: 0.7188 Epoch 9834/10000, Train Loss: 1.0215, Train Accuracy: 0.8906, Val Loss: 1.1752, Val Accuracy: 0.7143 Epoch 9835/10000, Train Loss: 1.0164, Train Accuracy: 0.8884, Val Loss: 1.1753, Val Accuracy: 0.7188 Epoch 9836/10000, Train Loss: 1.0272, Train Accuracy: 0.8862, Val Loss: 1.1748, Val Accuracy: 0.7188 Epoch 9837/10000, Train Loss: 1.0248, Train Accuracy: 0.8873, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9838/10000, Train Loss: 1.0256, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7232 Epoch 9839/10000, Train Loss: 1.0232, Train Accuracy: 0.8895, Val Loss: 1.1745, Val Accuracy: 0.7232 Epoch 9840/10000, Train Loss: 1.0340, Train Accuracy: 0.8728, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9841/10000, Train Loss: 1.0180, Train Accuracy: 0.8951, Val Loss: 1.1744, Val Accuracy: 0.7277 Epoch 9842/10000, Train Loss: 1.0277, Train Accuracy: 0.8873, Val Loss: 1.1743, Val Accuracy: 0.7366 Epoch 9843/10000, Train Loss: 1.0201, Train Accuracy: 0.8917, Val Loss: 1.1742, Val Accuracy: 0.7321 Epoch 9844/10000, Train Loss: 1.0305, Train Accuracy: 0.8806, Val Loss: 1.1742, Val Accuracy: 0.7366 Epoch 9845/10000, Train Loss: 1.0152, Train Accuracy: 0.9007, Val Loss: 1.1740, Val Accuracy: 0.7366 Epoch 9846/10000, Train Loss: 1.0230, Train Accuracy: 0.8828, Val Loss: 1.1739, Val Accuracy: 0.7366 Epoch 9847/10000, Train Loss: 1.0359, Train Accuracy: 0.8761, Val Loss: 1.1742, Val Accuracy: 0.7277 Epoch 9848/10000, Train Loss: 1.0264, Train Accuracy: 0.8917, Val Loss: 1.1741, Val Accuracy: 0.7366 Epoch 9849/10000, Train Loss: 1.0233, Train Accuracy: 0.8906, Val Loss: 1.1741, Val Accuracy: 0.7366 Epoch 9850/10000, Train Loss: 1.0121, Train Accuracy: 0.9007, Val Loss: 1.1739, Val Accuracy: 0.7366 Epoch 9851/10000, Train Loss: 1.0194, Train Accuracy: 0.8873, Val Loss: 1.1741, Val Accuracy: 0.7277 Epoch 9852/10000, Train Loss: 1.0203, Train Accuracy: 0.8873, Val Loss: 1.1742, Val Accuracy: 0.7277 Epoch 9853/10000, Train Loss: 1.0261, Train Accuracy: 0.8761, Val Loss: 1.1742, Val Accuracy: 0.7277 Epoch 9854/10000, Train Loss: 1.0232, Train Accuracy: 0.8884, Val Loss: 1.1739, Val Accuracy: 0.7277 Epoch 9855/10000, Train Loss: 1.0172, Train Accuracy: 0.8951, Val Loss: 1.1739, Val Accuracy: 0.7232 Epoch 9856/10000, Train Loss: 1.0195, Train Accuracy: 0.8962, Val Loss: 1.1737, Val Accuracy: 0.7232 Epoch 9857/10000, Train Loss: 1.0267, Train Accuracy: 0.8873, Val Loss: 1.1734, Val Accuracy: 0.7277 Epoch 9858/10000, Train Loss: 1.0361, Train Accuracy: 0.8705, Val Loss: 1.1737, Val Accuracy: 0.7188 Epoch 9859/10000, Train Loss: 1.0286, Train Accuracy: 0.8817, Val Loss: 1.1736, Val Accuracy: 0.7232 Epoch 9860/10000, Train Loss: 1.0324, Train Accuracy: 0.8806, Val Loss: 1.1737, Val Accuracy: 0.7232 Epoch 9861/10000, Train Loss: 1.0272, Train Accuracy: 0.8839, Val Loss: 1.1739, Val Accuracy: 0.7188 Epoch 9862/10000, Train Loss: 1.0281, Train Accuracy: 0.8850, Val Loss: 1.1737, Val Accuracy: 0.7232 Epoch 9863/10000, Train Loss: 1.0341, Train Accuracy: 0.8728, Val Loss: 1.1737, Val Accuracy: 0.7232 Epoch 9864/10000, Train Loss: 1.0306, Train Accuracy: 0.8839, Val Loss: 1.1738, Val Accuracy: 0.7232 Epoch 9865/10000, Train Loss: 1.0327, Train Accuracy: 0.8772, Val Loss: 1.1737, Val Accuracy: 0.7188 Epoch 9866/10000, Train Loss: 1.0214, Train Accuracy: 0.8884, Val Loss: 1.1739, Val Accuracy: 0.7188 Epoch 9867/10000, Train Loss: 1.0259, Train Accuracy: 0.8873, Val Loss: 1.1740, Val Accuracy: 0.7188 Epoch 9868/10000, Train Loss: 1.0275, Train Accuracy: 0.8839, Val Loss: 1.1742, Val Accuracy: 0.7143 Epoch 9869/10000, Train Loss: 1.0238, Train Accuracy: 0.8850, Val Loss: 1.1741, Val Accuracy: 0.7188 Epoch 9870/10000, Train Loss: 1.0175, Train Accuracy: 0.8951, Val Loss: 1.1744, Val Accuracy: 0.7188 Epoch 9871/10000, Train Loss: 1.0245, Train Accuracy: 0.8828, Val Loss: 1.1743, Val Accuracy: 0.7188 Epoch 9872/10000, Train Loss: 1.0211, Train Accuracy: 0.8929, Val Loss: 1.1744, Val Accuracy: 0.7143 Epoch 9873/10000, Train Loss: 1.0228, Train Accuracy: 0.8917, Val Loss: 1.1746, Val Accuracy: 0.7188 Epoch 9874/10000, Train Loss: 1.0325, Train Accuracy: 0.8750, Val Loss: 1.1742, Val Accuracy: 0.7188 Epoch 9875/10000, Train Loss: 1.0139, Train Accuracy: 0.8984, Val Loss: 1.1743, Val Accuracy: 0.7232 Epoch 9876/10000, Train Loss: 1.0262, Train Accuracy: 0.8873, Val Loss: 1.1743, Val Accuracy: 0.7232 Epoch 9877/10000, Train Loss: 1.0164, Train Accuracy: 0.8929, Val Loss: 1.1744, Val Accuracy: 0.7188 Epoch 9878/10000, Train Loss: 1.0192, Train Accuracy: 0.8940, Val Loss: 1.1745, Val Accuracy: 0.7143 Epoch 9879/10000, Train Loss: 1.0293, Train Accuracy: 0.8750, Val Loss: 1.1745, Val Accuracy: 0.7188 Epoch 9880/10000, Train Loss: 1.0301, Train Accuracy: 0.8795, Val Loss: 1.1748, Val Accuracy: 0.7188 Epoch 9881/10000, Train Loss: 1.0333, Train Accuracy: 0.8761, Val Loss: 1.1746, Val Accuracy: 0.7143 Epoch 9882/10000, Train Loss: 1.0351, Train Accuracy: 0.8772, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9883/10000, Train Loss: 1.0121, Train Accuracy: 0.8973, Val Loss: 1.1750, Val Accuracy: 0.7188 Epoch 9884/10000, Train Loss: 1.0059, Train Accuracy: 0.9074, Val Loss: 1.1750, Val Accuracy: 0.7188 Epoch 9885/10000, Train Loss: 1.0295, Train Accuracy: 0.8806, Val Loss: 1.1751, Val Accuracy: 0.7188 Epoch 9886/10000, Train Loss: 1.0259, Train Accuracy: 0.8862, Val Loss: 1.1754, Val Accuracy: 0.7143 Epoch 9887/10000, Train Loss: 1.0213, Train Accuracy: 0.8873, Val Loss: 1.1751, Val Accuracy: 0.7188 Epoch 9888/10000, Train Loss: 1.0147, Train Accuracy: 0.8996, Val Loss: 1.1749, Val Accuracy: 0.7232 Epoch 9889/10000, Train Loss: 1.0176, Train Accuracy: 0.8940, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9890/10000, Train Loss: 1.0266, Train Accuracy: 0.8862, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9891/10000, Train Loss: 1.0168, Train Accuracy: 0.8984, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9892/10000, Train Loss: 1.0275, Train Accuracy: 0.8862, Val Loss: 1.1746, Val Accuracy: 0.7232 Epoch 9893/10000, Train Loss: 1.0089, Train Accuracy: 0.9040, Val Loss: 1.1745, Val Accuracy: 0.7232 Epoch 9894/10000, Train Loss: 1.0215, Train Accuracy: 0.8884, Val Loss: 1.1749, Val Accuracy: 0.7232 Epoch 9895/10000, Train Loss: 1.0276, Train Accuracy: 0.8850, Val Loss: 1.1748, Val Accuracy: 0.7232 Epoch 9896/10000, Train Loss: 1.0206, Train Accuracy: 0.8951, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9897/10000, Train Loss: 1.0218, Train Accuracy: 0.8884, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9898/10000, Train Loss: 1.0205, Train Accuracy: 0.8906, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9899/10000, Train Loss: 1.0227, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7277 Epoch 9900/10000, Train Loss: 1.0190, Train Accuracy: 0.8862, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9901/10000, Train Loss: 1.0213, Train Accuracy: 0.8862, Val Loss: 1.1753, Val Accuracy: 0.7277 Epoch 9902/10000, Train Loss: 1.0357, Train Accuracy: 0.8761, Val Loss: 1.1750, Val Accuracy: 0.7277 Epoch 9903/10000, Train Loss: 1.0300, Train Accuracy: 0.8828, Val Loss: 1.1749, Val Accuracy: 0.7277 Epoch 9904/10000, Train Loss: 1.0162, Train Accuracy: 0.8984, Val Loss: 1.1747, Val Accuracy: 0.7277 Epoch 9905/10000, Train Loss: 1.0200, Train Accuracy: 0.8895, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9906/10000, Train Loss: 1.0282, Train Accuracy: 0.8828, Val Loss: 1.1746, Val Accuracy: 0.7232 Epoch 9907/10000, Train Loss: 1.0142, Train Accuracy: 0.9018, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9908/10000, Train Loss: 1.0185, Train Accuracy: 0.8962, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9909/10000, Train Loss: 1.0171, Train Accuracy: 0.8984, Val Loss: 1.1747, Val Accuracy: 0.7321 Epoch 9910/10000, Train Loss: 1.0186, Train Accuracy: 0.9018, Val Loss: 1.1746, Val Accuracy: 0.7277 Epoch 9911/10000, Train Loss: 1.0254, Train Accuracy: 0.8839, Val Loss: 1.1744, Val Accuracy: 0.7277 Epoch 9912/10000, Train Loss: 1.0215, Train Accuracy: 0.8895, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9913/10000, Train Loss: 1.0157, Train Accuracy: 0.9029, Val Loss: 1.1740, Val Accuracy: 0.7277 Epoch 9914/10000, Train Loss: 1.0282, Train Accuracy: 0.8806, Val Loss: 1.1737, Val Accuracy: 0.7277 Epoch 9915/10000, Train Loss: 1.0207, Train Accuracy: 0.8962, Val Loss: 1.1739, Val Accuracy: 0.7321 Epoch 9916/10000, Train Loss: 1.0286, Train Accuracy: 0.8850, Val Loss: 1.1741, Val Accuracy: 0.7321 Epoch 9917/10000, Train Loss: 1.0223, Train Accuracy: 0.8929, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9918/10000, Train Loss: 1.0326, Train Accuracy: 0.8783, Val Loss: 1.1744, Val Accuracy: 0.7277 Epoch 9919/10000, Train Loss: 1.0216, Train Accuracy: 0.8906, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9920/10000, Train Loss: 1.0291, Train Accuracy: 0.8772, Val Loss: 1.1740, Val Accuracy: 0.7321 Epoch 9921/10000, Train Loss: 1.0249, Train Accuracy: 0.8839, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9922/10000, Train Loss: 1.0218, Train Accuracy: 0.8850, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9923/10000, Train Loss: 1.0344, Train Accuracy: 0.8728, Val Loss: 1.1745, Val Accuracy: 0.7277 Epoch 9924/10000, Train Loss: 1.0104, Train Accuracy: 0.9051, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9925/10000, Train Loss: 1.0216, Train Accuracy: 0.8873, Val Loss: 1.1742, Val Accuracy: 0.7277 Epoch 9926/10000, Train Loss: 1.0094, Train Accuracy: 0.9074, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9927/10000, Train Loss: 1.0255, Train Accuracy: 0.8884, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9928/10000, Train Loss: 1.0191, Train Accuracy: 0.8895, Val Loss: 1.1744, Val Accuracy: 0.7232 Epoch 9929/10000, Train Loss: 1.0285, Train Accuracy: 0.8817, Val Loss: 1.1744, Val Accuracy: 0.7232 Epoch 9930/10000, Train Loss: 1.0218, Train Accuracy: 0.8895, Val Loss: 1.1743, Val Accuracy: 0.7321 Epoch 9931/10000, Train Loss: 1.0174, Train Accuracy: 0.8951, Val Loss: 1.1743, Val Accuracy: 0.7188 Epoch 9932/10000, Train Loss: 1.0150, Train Accuracy: 0.8951, Val Loss: 1.1744, Val Accuracy: 0.7188 Epoch 9933/10000, Train Loss: 1.0276, Train Accuracy: 0.8761, Val Loss: 1.1744, Val Accuracy: 0.7188 Epoch 9934/10000, Train Loss: 1.0258, Train Accuracy: 0.8783, Val Loss: 1.1747, Val Accuracy: 0.7143 Epoch 9935/10000, Train Loss: 1.0242, Train Accuracy: 0.8850, Val Loss: 1.1745, Val Accuracy: 0.7188 Epoch 9936/10000, Train Loss: 1.0219, Train Accuracy: 0.8929, Val Loss: 1.1742, Val Accuracy: 0.7188 Epoch 9937/10000, Train Loss: 1.0302, Train Accuracy: 0.8806, Val Loss: 1.1746, Val Accuracy: 0.7143 Epoch 9938/10000, Train Loss: 1.0114, Train Accuracy: 0.8996, Val Loss: 1.1743, Val Accuracy: 0.7188 Epoch 9939/10000, Train Loss: 1.0192, Train Accuracy: 0.8962, Val Loss: 1.1745, Val Accuracy: 0.7188 Epoch 9940/10000, Train Loss: 1.0265, Train Accuracy: 0.8795, Val Loss: 1.1745, Val Accuracy: 0.7188 Epoch 9941/10000, Train Loss: 1.0143, Train Accuracy: 0.8984, Val Loss: 1.1745, Val Accuracy: 0.7143 Epoch 9942/10000, Train Loss: 1.0208, Train Accuracy: 0.8884, Val Loss: 1.1746, Val Accuracy: 0.7143 Epoch 9943/10000, Train Loss: 1.0289, Train Accuracy: 0.8795, Val Loss: 1.1747, Val Accuracy: 0.7143 Epoch 9944/10000, Train Loss: 1.0251, Train Accuracy: 0.8850, Val Loss: 1.1744, Val Accuracy: 0.7143 Epoch 9945/10000, Train Loss: 1.0287, Train Accuracy: 0.8806, Val Loss: 1.1740, Val Accuracy: 0.7143 Epoch 9946/10000, Train Loss: 1.0168, Train Accuracy: 0.8996, Val Loss: 1.1739, Val Accuracy: 0.7188 Epoch 9947/10000, Train Loss: 1.0186, Train Accuracy: 0.8984, Val Loss: 1.1738, Val Accuracy: 0.7188 Epoch 9948/10000, Train Loss: 1.0251, Train Accuracy: 0.8806, Val Loss: 1.1736, Val Accuracy: 0.7188 Epoch 9949/10000, Train Loss: 1.0256, Train Accuracy: 0.8817, Val Loss: 1.1735, Val Accuracy: 0.7277 Epoch 9950/10000, Train Loss: 1.0234, Train Accuracy: 0.8839, Val Loss: 1.1736, Val Accuracy: 0.7277 Epoch 9951/10000, Train Loss: 1.0243, Train Accuracy: 0.8895, Val Loss: 1.1736, Val Accuracy: 0.7277 Epoch 9952/10000, Train Loss: 1.0083, Train Accuracy: 0.9029, Val Loss: 1.1737, Val Accuracy: 0.7277 Epoch 9953/10000, Train Loss: 1.0248, Train Accuracy: 0.8850, Val Loss: 1.1738, Val Accuracy: 0.7232 Epoch 9954/10000, Train Loss: 1.0239, Train Accuracy: 0.8850, Val Loss: 1.1736, Val Accuracy: 0.7277 Epoch 9955/10000, Train Loss: 1.0303, Train Accuracy: 0.8806, Val Loss: 1.1735, Val Accuracy: 0.7277 Epoch 9956/10000, Train Loss: 1.0148, Train Accuracy: 0.8973, Val Loss: 1.1738, Val Accuracy: 0.7277 Epoch 9957/10000, Train Loss: 1.0207, Train Accuracy: 0.8917, Val Loss: 1.1738, Val Accuracy: 0.7232 Epoch 9958/10000, Train Loss: 1.0170, Train Accuracy: 0.9007, Val Loss: 1.1738, Val Accuracy: 0.7232 Epoch 9959/10000, Train Loss: 1.0234, Train Accuracy: 0.8895, Val Loss: 1.1736, Val Accuracy: 0.7277 Epoch 9960/10000, Train Loss: 1.0217, Train Accuracy: 0.8873, Val Loss: 1.1737, Val Accuracy: 0.7277 Epoch 9961/10000, Train Loss: 1.0205, Train Accuracy: 0.8884, Val Loss: 1.1738, Val Accuracy: 0.7232 Epoch 9962/10000, Train Loss: 1.0146, Train Accuracy: 0.9018, Val Loss: 1.1741, Val Accuracy: 0.7277 Epoch 9963/10000, Train Loss: 1.0227, Train Accuracy: 0.8940, Val Loss: 1.1745, Val Accuracy: 0.7232 Epoch 9964/10000, Train Loss: 1.0252, Train Accuracy: 0.8862, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9965/10000, Train Loss: 1.0147, Train Accuracy: 0.8951, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9966/10000, Train Loss: 1.0205, Train Accuracy: 0.8929, Val Loss: 1.1748, Val Accuracy: 0.7188 Epoch 9967/10000, Train Loss: 1.0244, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7188 Epoch 9968/10000, Train Loss: 1.0170, Train Accuracy: 0.8951, Val Loss: 1.1749, Val Accuracy: 0.7188 Epoch 9969/10000, Train Loss: 1.0251, Train Accuracy: 0.8828, Val Loss: 1.1748, Val Accuracy: 0.7188 Epoch 9970/10000, Train Loss: 1.0128, Train Accuracy: 0.9007, Val Loss: 1.1751, Val Accuracy: 0.7143 Epoch 9971/10000, Train Loss: 1.0299, Train Accuracy: 0.8806, Val Loss: 1.1751, Val Accuracy: 0.7143 Epoch 9972/10000, Train Loss: 1.0283, Train Accuracy: 0.8750, Val Loss: 1.1752, Val Accuracy: 0.7143 Epoch 9973/10000, Train Loss: 1.0452, Train Accuracy: 0.8683, Val Loss: 1.1749, Val Accuracy: 0.7188 Epoch 9974/10000, Train Loss: 1.0196, Train Accuracy: 0.8940, Val Loss: 1.1749, Val Accuracy: 0.7188 Epoch 9975/10000, Train Loss: 1.0227, Train Accuracy: 0.8862, Val Loss: 1.1748, Val Accuracy: 0.7232 Epoch 9976/10000, Train Loss: 1.0279, Train Accuracy: 0.8850, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9977/10000, Train Loss: 1.0136, Train Accuracy: 0.8984, Val Loss: 1.1746, Val Accuracy: 0.7188 Epoch 9978/10000, Train Loss: 1.0192, Train Accuracy: 0.8940, Val Loss: 1.1745, Val Accuracy: 0.7232 Epoch 9979/10000, Train Loss: 1.0173, Train Accuracy: 0.8984, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9980/10000, Train Loss: 1.0206, Train Accuracy: 0.8884, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9981/10000, Train Loss: 1.0154, Train Accuracy: 0.9007, Val Loss: 1.1747, Val Accuracy: 0.7232 Epoch 9982/10000, Train Loss: 1.0134, Train Accuracy: 0.9007, Val Loss: 1.1745, Val Accuracy: 0.7232 Epoch 9983/10000, Train Loss: 1.0073, Train Accuracy: 0.9029, Val Loss: 1.1743, Val Accuracy: 0.7277 Epoch 9984/10000, Train Loss: 1.0190, Train Accuracy: 0.8917, Val Loss: 1.1744, Val Accuracy: 0.7232 Epoch 9985/10000, Train Loss: 1.0304, Train Accuracy: 0.8783, Val Loss: 1.1743, Val Accuracy: 0.7232 Epoch 9986/10000, Train Loss: 1.0153, Train Accuracy: 0.8951, Val Loss: 1.1745, Val Accuracy: 0.7232 Epoch 9987/10000, Train Loss: 1.0243, Train Accuracy: 0.8828, Val Loss: 1.1743, Val Accuracy: 0.7232 Epoch 9988/10000, Train Loss: 1.0157, Train Accuracy: 0.8973, Val Loss: 1.1740, Val Accuracy: 0.7232 Epoch 9989/10000, Train Loss: 1.0206, Train Accuracy: 0.8862, Val Loss: 1.1742, Val Accuracy: 0.7188 Epoch 9990/10000, Train Loss: 1.0164, Train Accuracy: 0.8951, Val Loss: 1.1743, Val Accuracy: 0.7188 Epoch 9991/10000, Train Loss: 1.0208, Train Accuracy: 0.8917, Val Loss: 1.1741, Val Accuracy: 0.7188 Epoch 9992/10000, Train Loss: 1.0256, Train Accuracy: 0.8862, Val Loss: 1.1741, Val Accuracy: 0.7188 Epoch 9993/10000, Train Loss: 1.0154, Train Accuracy: 0.9029, Val Loss: 1.1744, Val Accuracy: 0.7188 Epoch 9994/10000, Train Loss: 1.0026, Train Accuracy: 0.9107, Val Loss: 1.1744, Val Accuracy: 0.7188 Epoch 9995/10000, Train Loss: 1.0172, Train Accuracy: 0.8895, Val Loss: 1.1741, Val Accuracy: 0.7188 Epoch 9996/10000, Train Loss: 1.0224, Train Accuracy: 0.8940, Val Loss: 1.1739, Val Accuracy: 0.7188 Epoch 9997/10000, Train Loss: 1.0237, Train Accuracy: 0.8940, Val Loss: 1.1740, Val Accuracy: 0.7188 Epoch 9998/10000, Train Loss: 1.0233, Train Accuracy: 0.8906, Val Loss: 1.1738, Val Accuracy: 0.7188 Epoch 9999/10000, Train Loss: 1.0288, Train Accuracy: 0.8806, Val Loss: 1.1734, Val Accuracy: 0.7188 Epoch 10000/10000, Train Loss: 1.0230, Train Accuracy: 0.8850, Val Loss: 1.1733, Val Accuracy: 0.7188
torch.save(model_nn.state_dict(), best_model_path_nn)
# Load the best model
model_nn.load_state_dict(torch.load(best_model_path_nn))
<All keys matched successfully>
# Evaluate on test data
model_nn.eval()
X_test_tensor = torch.tensor(X_test.values, dtype=torch.float32)
y_test_tensor = torch.tensor(y_test.values, dtype=torch.long) # Use long for class indices
with torch.no_grad():
test_output = model_nn(X_test_tensor)
test_loss = criterion(test_output, y_test_tensor)
test_predictions = torch.argmax(test_output, dim=1) # Get the predicted class indices
test_correct = (test_predictions == y_test_tensor).sum().item()
test_total = y_test_tensor.size(0)
test_acc = test_correct / test_total
print(f'Test Loss: {test_loss.item():.4f}, Test Accuracy: {test_acc:.4f}')
Test Loss: 1.1447, Test Accuracy: 0.7500
The final test accuracy of the neural network is 75.00% which is better then the one of all the best models found so far (Random Forest with Bayesian Search and KNN with grid Search). However, neural networks models usually reach an higher accuracy. In this case, the relatively low accuracy could be primarily attributed to the dataset's limited size, consisting of only 1400 data points.
Given that the dataset was further split into training and testing sets (80% training and 20% testing), and then the training set was again split into 80% training and 20% validation, the neural network had even fewer data points to learn from. This limited data hindered the model's ability to fully learn the complex patterns and features within the dataset.
A potential solution to address this issue could be to implement a Boltzmann machine. After training the Boltzmann machine, it could generate new data points with the same probability distributions as the original dataset, thus providing a larger volume of data for training the neural network. However, due to time constraints and the fact that this approach is beyond the scope of the current project, this possibility will not be explored further.
¶
- PREDICTIONS
Now I am going to predict the class of the anonymous data points provided by the professor
anonymous_data = pd.read_csv('mldata_0003195463/mldata_0003195463.TEST_FEATURES.csv', index_col=0)
anonymous_data
| feature_1 | feature_2 | feature_3 | feature_4 | feature_5 | feature_6 | feature_7 | feature_8 | feature_9 | feature_10 | ... | feature_16 | feature_17 | feature_18 | feature_19 | feature_20 | feature_21 | feature_22 | feature_23 | feature_24 | feature_25 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| id | |||||||||||||||||||||
| 0 | -1.583901 | 0.066270 | 0.462274 | -0.175453 | -0.122860 | -2.964932 | -1.128756 | -1.583901 | -0.837369 | -1.541634 | ... | 2.058315 | 1.987120 | 0.875662 | 0.490501 | -0.564009 | -0.473025 | -3.121843 | -3.204708 | 4.059989 | -1.230859 |
| 1 | 0.741998 | 0.842662 | -0.580674 | 1.177410 | -1.590579 | -0.992677 | 1.202091 | 0.741998 | 0.397817 | 0.878938 | ... | -2.693609 | 2.358702 | -0.448296 | 1.258434 | -0.929838 | 0.551937 | 1.675974 | 2.500228 | -1.905566 | 0.004239 |
| 2 | -2.690293 | -1.274130 | 3.564006 | 0.840850 | -1.267567 | -0.168341 | 2.832282 | -2.690293 | -2.031966 | 1.289001 | ... | 5.708247 | -1.422307 | 0.561772 | 5.098278 | 2.644700 | -0.522982 | 0.559692 | -2.000696 | 2.440799 | 0.144461 |
| 3 | -1.449382 | 1.068814 | -3.820457 | -0.836199 | -1.242546 | -1.803914 | 0.858350 | -1.449382 | -3.473241 | 1.331370 | ... | 1.037856 | -3.569374 | 0.000523 | 4.939084 | -2.669314 | -0.229439 | -1.235043 | -2.255308 | 4.259756 | 0.219297 |
| 4 | -0.001136 | 4.266773 | 0.390607 | -0.230595 | 0.055867 | -0.388356 | 0.298274 | -0.001136 | 2.720829 | 0.960466 | ... | -1.661571 | 2.500116 | 0.314138 | 2.876392 | 0.793374 | 0.016719 | -1.138375 | 0.867594 | 0.588746 | 1.752658 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 1395 | 3.051612 | 5.335903 | -0.780311 | -1.206728 | 6.041506 | -2.462116 | -0.099222 | 3.051612 | -0.541221 | 0.031599 | ... | -2.389265 | -1.532996 | 0.165623 | -0.557866 | 2.452305 | -1.016575 | -0.347464 | -4.107339 | 4.148608 | -0.819975 |
| 1396 | -0.818027 | 0.131502 | -3.361555 | 0.574756 | -1.395142 | -2.137571 | 2.059778 | -0.818027 | 4.986959 | 0.337357 | ... | 2.695408 | -2.043497 | 0.417200 | 4.119033 | -1.835029 | -1.014946 | 0.459286 | 0.252998 | -5.875338 | -0.483199 |
| 1397 | 1.300382 | 4.959589 | -0.821422 | 0.048367 | -1.133989 | 2.583393 | 3.246328 | 1.300382 | 1.914509 | 0.360079 | ... | 0.811838 | 4.422174 | -1.072638 | 4.729813 | -2.414941 | 1.112228 | 0.541504 | 1.608467 | -0.122532 | 0.698078 |
| 1398 | -3.811468 | -0.570010 | 0.967775 | -0.904938 | -2.729183 | -3.508922 | 0.989772 | -3.811468 | -2.331983 | 1.343327 | ... | -1.978188 | 0.218630 | 0.657534 | 6.934419 | 1.609578 | -1.178043 | -0.004904 | 3.420006 | 1.526097 | -0.750451 |
| 1399 | 2.115240 | 3.851803 | -0.699010 | -1.335313 | -0.850509 | 0.122552 | 1.786011 | 2.115240 | 0.213781 | -1.410630 | ... | -1.658974 | 1.958692 | 0.723056 | 6.628800 | -1.487204 | 0.189379 | -0.214925 | 1.151181 | 5.037282 | 1.696641 |
1400 rows × 25 columns
As anticipated before I am now going to predict the class of the anonymous data using the best model, the Random Forest classifier whose hyperparameters have been set with the Bayesian Search. Moreover I will also compare these predictions with the one made by the KNN (the one whose hyperparameters have been established by the Grid Search) in order to find similarities.
final_an_predictions = best_rf_bayes.predict(anonymous_data)
# check the predictions respect the format, etc
final_an_predictions, len(final_an_predictions), set(final_an_predictions)
(array([0, 1, 0, ..., 1, 0, 1]), 1400, {0, 1, 2, 3, 4})
# let try now with the KNN best model to see how many similar predictions we get
final_an_predictions_knn = best_knn_grid.predict(anonymous_data)
final_an_predictions_knn, len(final_an_predictions_knn), set(final_an_predictions_knn)
(array([0, 1, 0, ..., 1, 0, 1]), 1400, {0, 1, 2, 3, 4})
k=0
for i in range(1400):
if final_an_predictions[i]!=final_an_predictions_knn[i]:
k=k+1
print("RF VS KNN", "\nnumber errors: ", k, "\npercentage correspondance: ", (1400-k)/1400)
RF VS KNN number errors: 317 percentage correspondance: 0.7735714285714286
It is possible to notice that the correspondece between RF and KNN is of 77%, that potentially could also represent the percentages of right predictions (I still don't know on the different predictions which model is right).
Finally I save the prediction (I will send the predictions made by the random forest for the reasons explain in the former section, Final Model Evaluation) on a separate file.
np.savetxt('test_predictions_Federico_Pezzoli_ML_Project.txt', final_an_predictions, fmt='%d')
¶
- CONCLUSIONS
In this project, the primary goal was to compare the performance of the k-Nearest Neighbors (KNN) algorithm with that of a Random Forest classifier on the given dataset. Additionally, I carried out an exploratory data analysis, the use of pca and implementation of a Neural Network to further understand the dataset and explore if a more complex model could improve the performance.
KEY FINDINGS:
- The best model found (excluded the Neural Network which was an extra topic) was the Random Forest classifier with Bayesian Search (for details about the parameters go to the section Model Selection), achieving an accuracy of 73%. This performance is not incredibly satisfying and this is probably caused by the fact that the data in this case is not easily separable leading to overfitting and higher test error.
- the KNN classifier instead performed consistently across different hyperparameter tuning methods, with the best accuracy being around 71% (lower then the one mentioned above). KNN has the advantage of being a non-parametric method, meaning it does not make specific assumptions about the data's distribution and shape. However, here KNN seems to be too simple to capture the underlying patterns in the data and correctly classify it.
CHALLENGES AND FUTURE POSSIBLE IMPROVEMENTS:
- the dataset was not particular large since it just contained 1400 data points making difficult to train appropriately more complex models as neural networks.
- In the KNN an additional scaling of the data did not significantly impact it; this was unexpected and suggests that other factors might be influencing the model's performance (additional scaling steps, using for example Standard Scaler or MinMax scaler have not been reported here given the length of the report and the useless impact they had, but they are mentioned to give a broader view of the context).
- additional hyperparameter tuning and model optimization techniques could be applied to improve the performance of the models. For example, testing a broader range of values for cross-validation folds or other hyperparameters could yield better results (in our case for example I mainly limited my work to values of cross validation between 3 and 6 given the time and computational constraints).
- other ML models like SVM with non-linear kernels or other ensemble learning methods as gradient Boosting (usually more powerful then RF) could be implemented.